© 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. 10745
    Prev
    Next
    INDEX
    Explanations

    adjectives or verbs related to being impressed or impressed by something

    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
    +0.18
    0.6%
    255
    +0.16
    0.5%
    117
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.09
    326
    +0.16
    0.08
    555
    +0.16
    0.05
    Negative Logits
    interrupted
    -1.13
    nect
    -0.99
     amino
    -0.99
    alde
    -0.95
    stitial
    -0.94
    ford
    -0.92
    ylene
    -0.91
    sil
    -0.89
     sovere
    -0.86
    ttp
    -0.86
    POSITIVE LOGITS
    ments
    1.21
    mented
    1.18
    ively
    1.07
    eting
    1.04
    ered
    1.01
     impressed
    0.97
    MENTS
    0.96
    ment
    0.94
    »
    0.94
    ulously
    0.93
    Activations Density 1.254%

    No Known Activations