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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2186
    Prev
    Next
    INDEX
    Explanations

    words related to technological features or characteristics

    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
    0.7%
    195
    +0.16
    0.5%
    317
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.23
    0.07
    540
    +0.16
    0.07
    211
    +0.16
    0.02
    Negative Logits
    sis
    -1.16
    cffffcc
    -1.15
    alg
    -1.11
    ça
    -1.09
    eneg
    -1.08
    oner
    -1.07
    aline
    -1.04
    cel
    -1.03
    hur
    -1.00
    agher
    -0.99
    POSITIVE LOGITS
    ivity
    1.15
    hered
    1.15
    ttes
    1.14
    ioned
    1.12
    Features
    1.12
    Feature
    1.11
    iveness
    1.10
     features
    1.05
     Features
    1.04
     prominently
    1.01
    Activations Density 1.172%

    No Known Activations