© 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. 45858
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an unconditional or indiscriminate quality or condition

    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
    447
    +0.21
    0.9%
    679
    +0.15
    0.7%
    739
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    558
    +0.21
    0.07
    513
    +0.15
    0.07
    434
    +0.12
    0.06
    Negative Logits
    ahime
    -0.99
    ohyd
    -0.80
    eria
    -0.80
    eries
    -0.79
    asus
    -0.75
    anz
    -0.74
    erie
    -0.74
    ãĥ¼ãĥ³
    -0.72
    berus
    -0.72
    sels
    -0.72
    POSITIVE LOGITS
     includ
    0.75
    wcs
    0.71
     remotely
    0.70
     whatsoever
    0.70
     irrespective
    0.69
    etheless
    0.69
    theless
    0.68
     athlet
    0.68
    handedly
    0.68
     thereafter
    0.67
    Activations Density 5.562%

    No Known Activations