© 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. 3180
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking no action or remaining inactive

    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
    620
    +0.20
    0.6%
    383
    +0.18
    0.6%
    665
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    383
    +0.20
    0.06
    191
    +0.18
    0.03
    737
    +0.17
    0.04
    Negative Logits
    midt
    -1.09
     Submission
    -1.08
    CVE
    -0.99
    ymph
    -0.96
    ilt
    -0.95
     Appeal
    -0.93
    onym
    -0.92
    andi
    -0.91
    assis
    -0.91
     srf
    -0.91
    POSITIVE LOGITS
     else
    1.70
    Else
    1.28
     whatsoever
    1.26
     remotely
    1.17
     imaginable
    1.13
    conom
    1.06
    ness
    1.02
    pie
    1.02
     Else
    1.00
     resembling
    0.99
    Activations Density 0.296%

    No Known Activations