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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14028
    Prev
    Next
    INDEX
    Explanations

    reports of deaths by various causes, particularly emphasizing suicides in different contexts and professions

    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
    260
    +0.03
    0.5%
    494
    +0.03
    0.4%
    178
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.03
    0.06
    16
    +0.03
    0.04
    132
    +0.03
    0.04
    Negative Logits
    elta
    -0.22
     sclerosis
    -0.19
    abil
    -0.19
    ilib
    -0.19
    fare
    -0.19
    robe
    -0.19
    mir
    -0.19
    hair
    -0.19
    ocr
    -0.18
    ocrates
    -0.18
    POSITIVE LOGITS
     suicides
    0.23
     Tasman
    0.20
     Manit
    0.20
    igans
    0.19
    ipeg
    0.19
     ponds
    0.17
    istics
    0.17
    izations
    0.17
    itives
    0.17
    uates
    0.17
    Activations Density 0.524%

    No Known Activations