© 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. 32842
    Prev
    Next
    INDEX
    Explanations

    words related to individuals' accomplishments, activities, and personal stories

    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
    +0.10
    0.6%
    128
    +0.09
    0.5%
    643
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    643
    +0.10
    0.06
    112
    +0.09
    0.08
    556
    +0.08
    0.08
    Negative Logits
    tale
    -0.58
    DragonMagazine
    -0.57
    OLOGY
    -0.56
     Tale
    -0.56
    RIC
    -0.56
    ramid
    -0.54
    Ĥİ
    -0.53
    bish
    -0.53
    bial
    -0.52
    amaru
    -0.52
    POSITIVE LOGITS
    aunch
    0.93
    ocations
    0.87
    apsed
    0.85
    abel
    0.84
    aun
    0.82
    ocating
    0.81
    apses
    0.80
    ight
    0.78
    atable
    0.76
    ocation
    0.76
    Activations Density 5.209%

    No Known Activations