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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3338
    Prev
    Next
    INDEX
    Explanations

    file paths in a computer system and commands related to computer programming

    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
    393
    +0.16
    0.6%
    481
    +0.13
    0.5%
    699
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.16
    0.03
    257
    +0.13
    0.04
    380
    +0.13
    0.03
    Negative Logits
     arrang
    -0.97
     agre
    -0.93
     reconc
    -0.91
     enthusi
    -0.86
     alterations
    -0.85
     compromises
    -0.80
     alteration
    -0.79
    TPPStreamerBot
    -0.79
     unheard
    -0.79
     exposition
    -0.76
    POSITIVE LOGITS
    ragon
    0.92
     Stainless
    0.89
    Merit
    0.87
    ulo
    0.82
    Æ
    0.82
     ®
    0.81
     Vlad
    0.81
     CFR
    0.79
    tesy
    0.78
    cum
    0.78
    Activations Density 0.456%

    No Known Activations