© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 40543
    Prev
    Next
    INDEX
    Explanations

    words related to personal experiences and beliefs

    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
    +0.22
    1.1%
    326
    +0.11
    0.6%
    640
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.22
    0.20
    232
    +0.11
    0.13
    283
    +0.10
    0.05
    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.80
    ously
    -0.69
    uers
    -0.65
    ratulations
    -0.64
    ãĥ³ãĤ¸
    -0.59
     Galile
    -0.59
     aven
    -0.59
     suspic
    -0.58
     TAMADRA
    -0.58
    orescence
    -0.58
    POSITIVE LOGITS
    etc
    0.91
    walking
    0.82
     fixme
    0.75
    please
    0.73
    where
    0.73
    they
    0.70
    ordered
    0.69
    SER
    0.69
    sound
    0.68
    999
    0.67
    Activations Density 7.968%

    No Known Activations