© 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 Local
    9. 6-RES_SCL-AJT
    11. 33089
    Prev
    Next
    INDEX
    Explanations

    phrases related to political figures and positions, as well as actions and insights involving relationships between characters

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    302
    +0.12
    0.6%
    99
    +0.10
    0.5%
    566
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.21
    288
    +0.10
    0.21
    302
    +0.10
    0.12
    Negative Logits
    Availability
    -0.73
    Rated
    -0.71
    ENC
    -0.69
     srfAttach
    -0.67
    ×IJ
    -0.66
    NRS
    -0.64
     Ezek
    -0.63
     fracturing
    -0.63
     Beir
    -0.60
    USB
    -0.59
    POSITIVE LOGITS
    shaw
    0.96
    ãĥ£
    0.91
    itives
    0.91
    yright
    0.91
    erate
    0.90
    eer
    0.89
    gements
    0.88
    oir
    0.87
    eers
    0.87
    iversal
    0.85
    Activations Density 6.523%

    No Known Activations