© 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. 34732
    Prev
    Next
    INDEX
    Explanations

    names of individuals mentioned within the text

    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
    497
    +0.10
    0.6%
    383
    +0.10
    0.6%
    187
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.10
    0.18
    288
    +0.10
    0.18
    187
    +0.10
    0.10
    Negative Logits
    stal
    -0.64
    vation
    -0.64
    ension
    -0.63
    ory
    -0.60
    ization
    -0.56
    ¦
    -0.56
    itri
    -0.56
    ruction
    -0.56
    stall
    -0.55
    strate
    -0.55
    POSITIVE LOGITS
    awatts
    0.62
     Jem
    0.60
    Reviewer
    0.60
    itsch
    0.60
    oro
    0.60
    wei
    0.58
    irk
    0.58
    vertisement
    0.57
    raft
    0.56
    hart
    0.56
    Activations Density 5.055%

    No Known Activations