© 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. 13723
    Prev
    Next
    INDEX
    Explanations

    events related to news and politics, particularly focusing on activist movements and government 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
    288
    +0.22
    0.7%
    238
    +0.18
    0.6%
    79
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.22
    0.10
    326
    +0.18
    0.08
    99
    +0.15
    0.06
    Negative Logits
    æĸ¹
    -1.21
    perty
    -1.15
    vironment
    -1.12
    OHN
    -1.12
    ushima
    -1.08
    CRIP
    -1.04
    MODE
    -1.02
    hire
    -0.99
    opausal
    -0.99
    EMENT
    -0.97
    POSITIVE LOGITS
    itudinal
    1.52
    itude
    1.47
    itud
    1.43
    itudes
    1.28
    robe
    1.27
    akia
    1.21
    imes
    1.19
    imore
    1.14
    ency
    1.13
    ting
    1.12
    Activations Density 1.226%

    No Known Activations