© 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. 1644
    Prev
    Next
    INDEX
    Explanations

    mentions of licensing, especially in the context of legal documents

    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
    767
    +0.16
    0.6%
    746
    +0.14
    0.5%
    569
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.05
    767
    +0.14
    0.03
    326
    +0.14
    0.04
    Negative Logits
    izoph
    -0.95
     Unch
    -0.94
     Ended
    -0.92
     Lans
    -0.91
     Samoa
    -0.86
    DERR
    -0.84
     Recomm
    -0.83
    thing
    -0.81
    åĤ
    -0.81
    Discussion
    -0.80
    POSITIVE LOGITS
    ensing
    1.86
    enses
    1.63
    hess
    1.33
    entious
    1.24
    umin
    1.21
    ulty
    1.20
    ious
    1.19
    hester
    1.17
    ensor
    1.12
    ornia
    1.12
    Activations Density 0.394%

    No Known Activations