© 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. 1704
    Prev
    Next
    INDEX
    Explanations

    descriptions related to security and crime investigations

    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
    344
    +0.13
    0.5%
    58
    +0.12
    0.5%
    680
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    58
    +0.13
    0.05
    522
    +0.12
    0.07
    344
    +0.11
    0.07
    Negative Logits
     srfAttach
    -0.82
    EMA
    -0.80
    âĵĺ
    -0.76
    Atl
    -0.75
    fleet
    -0.74
    CHAT
    -0.70
    anca
    -0.69
     Et
    -0.69
    IRT
    -0.69
     Rober
    -0.69
    POSITIVE LOGITS
     technically
    1.06
     initially
    0.98
     ostensibly
    0.95
     outward
    0.79
     theoretically
    0.79
     sounds
    0.76
     admittedly
    0.74
     laud
    0.74
    omical
    0.73
     physically
    0.73
    Activations Density 2.537%

    No Known Activations