© 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 EvalsExportsinterp-engineNEWAPI 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. 8297
    Prev
    Next
    INDEX
    Explanations

    information related to academic discussions, treatments, and stories of historical or fictional figures

    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
    308
    +0.15
    0.6%
    254
    +0.12
    0.4%
    555
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    254
    +0.15
    0.05
    107
    +0.12
    0.03
    514
    +0.12
    0.04
    Negative Logits
    GGGG
    -0.99
    boa
    -0.86
    emouth
    -0.81
    cloth
    -0.76
     McMaster
    -0.76
    yip
    -0.75
    ãĥĩãĤ£
    -0.74
    senal
    -0.74
     RN
    -0.73
    ansas
    -0.73
    POSITIVE LOGITS
    ¹
    1.02
    etheus
    1.01
    rates
    0.98
    rules
    0.98
    §
    0.94
    Ĺ
    0.94
    ¥
    0.93
    Ĥ
    0.93
    ution
    0.93
    furt
    0.92
    Activations Density 0.521%

    No Known Activations