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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 32411
    Prev
    Next
    INDEX
    Explanations

    words related to learning, education, and intellectual development

    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
    481
    +0.20
    0.9%
    447
    +0.15
    0.7%
    724
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.20
    0.15
    288
    +0.15
    0.22
    255
    +0.10
    0.13
    Negative Logits
    onal
    -0.77
    ouk
    -0.75
    cise
    -0.71
    Sund
    -0.71
    ãĥ¼ãĥĨãĤ£
    -0.69
    ishable
    -0.68
    RL
    -0.68
    eday
    -0.66
    CAST
    -0.66
     Tanz
    -0.66
    POSITIVE LOGITS
    iness
    0.91
    fulness
    0.90
    abilities
    0.88
    lessness
    0.82
     perv
    0.81
    smanship
    0.80
    lust
    0.80
    cles
    0.80
    ability
    0.78
    butt
    0.78
    Activations Density 7.942%

    No Known Activations