© 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. 1
    Prev
    Next
    INDEX
    Explanations

    phrases and sentences that emphasize collaboration and unity

    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
    618
    +0.19
    0.6%
    214
    +0.18
    0.6%
    101
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    101
    +0.19
    0.06
    618
    +0.18
    0.05
    214
    +0.17
    0.04
    Negative Logits
    ysis
    -1.29
    anty
    -1.01
    ounty
    -1.00
    ocalypse
    -0.95
    ortal
    -0.95
    imi
    -0.93
    olis
    -0.90
    geries
    -0.90
     Zam
    -0.90
     Hive
    -0.89
    POSITIVE LOGITS
    ness
    1.05
    ãĤ¤ãĥĪ
    1.03
     ranks
    0.98
    BY
    0.97
     induct
    0.97
    NESS
    0.95
    ãĥĵ
    0.94
     reun
    0.93
    姫
    0.92
    åij
    0.92
    Activations Density 0.574%

    No Known Activations