© 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. 40542
    Prev
    Next
    INDEX
    Explanations

    words related to cognitive functions and mental health

    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
    288
    +0.16
    0.9%
    447
    +0.14
    0.8%
    99
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    365
    +0.16
    0.03
    381
    +0.14
    0.08
    285
    +0.12
    0.04
    Negative Logits
    FORE
    -0.65
    coni
    -0.64
    encer
    -0.64
    export
    -0.63
    EGA
    -0.63
    andro
    -0.62
    olicited
    -0.61
     Leone
    -0.60
    ourced
    -0.58
    enta
    -0.58
    POSITIVE LOGITS
     disson
    1.23
     enh
    1.00
     faculties
    0.88
     enhancement
    0.80
     impairment
    0.79
     behavioural
    0.75
     hygiene
    0.73
    ly
    0.73
     abilities
    0.70
    istically
    0.69
    Activations Density 8.386%

    No Known Activations