© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 45
    Prev
    Next
    INDEX
    Explanations

    verbs related to physical movement or actions, such as waving, rippling, and bouncing

    oai_token-act-pair · gpt-3.5-turbo
    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
    +0.23
    0.8%
    578
    +0.15
    0.5%
    129
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.23
    0.06
    288
    +0.15
    0.07
    129
    +0.14
    0.05
    Negative Logits
    heid
    -1.21
    orate
    -1.17
    azeera
    -1.04
    atem
    -1.03
    ioch
    -1.00
    rontal
    -1.00
    berra
    -0.96
    ately
    -0.96
    uments
    -0.96
    inez
    -0.95
    POSITIVE LOGITS
    guide
    1.35
    front
    1.29
    form
    1.20
    stakes
    1.17
    boat
    1.16
     wave
    1.13
    rers
    1.11
    Wave
    1.10
    forms
    1.09
     goodbye
    1.08
    Activations Density 0.846%

    No Known Activations