© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 13685
    Prev
    Next
    INDEX
    Explanations

    phrases related to changing or turning things around

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "flip" or variations of flipping actions

    oai_token-act-pair · gpt-3.5-turboTriggered by @danbraun
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.24
    0.9%
    195
    +0.20
    0.7%
    189
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.24
    0.07
    189
    +0.20
    0.05
    326
    +0.17
    0.05
    Negative Logits
    Interstitial
    -1.09
    aph
    -1.02
    lain
    -0.99
     Territories
    -0.97
    FORE
    -0.96
     Continued
    -0.93
    mble
    -0.89
    mma
    -0.87
     Palest
    -0.85
     Begin
    -0.84
    POSITIVE LOGITS
     flip
    1.09
     flips
    1.04
     burgers
    1.04
     flipped
    1.03
    nir
    1.03
     flipping
    1.02
    olitics
    1.01
    switch
    0.99
    tera
    0.98
    wheel
    0.97
    Activations Density 0.697%

    No Known Activations