© 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 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. 12321
    Prev
    Next
    INDEX
    Explanations

    religious or biblical references, specifically related to powerful or divine entities and their actions

    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
    527
    +0.05
    0.5%
    608
    +0.05
    0.5%
    323
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.05
    0.04
    524
    +0.05
    0.04
    148
    +0.05
    0.04
    Negative Logits
    etts
    -0.45
    mble
    -0.44
    raints
    -0.42
    etta
    -0.41
    zai
    -0.41
    etic
    -0.41
    orescent
    -0.39
    eways
    -0.39
    phis
    -0.39
     partName
    -0.38
    POSITIVE LOGITS
     Lug
    0.38
     SEAL
    0.36
    alog
    0.36
     unto
    0.36
    selves
    0.35
     theirs
    0.34
     Oath
    0.34
    anche
    0.32
     Caesar
    0.32
    fish
    0.32
    Activations Density 0.433%

    No Known Activations