Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 34117
    Prev
    Next
    INDEX
    Explanations

    phrases related to various topics and subjects, possibly indicating a broad interest in learning and knowledge

    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
    +0.20
    0.9%
    326
    +0.13
    0.6%
    200
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.20
    0.30
    138
    +0.13
    0.28
    64
    +0.12
    -0.22
    Negative Logits
    holder
    -0.82
    ivities
    -0.78
    puter
    -0.73
    ancies
    -0.72
    rap
    -0.72
    selves
    -0.71
    uates
    -0.70
     comr
    -0.66
    atche
    -0.65
     quarters
    -0.64
    POSITIVE LOGITS
    ppo
    1.24
    zzi
    1.17
    cean
    1.16
    ctl
    1.09
    ffic
    1.04
    ption
    1.02
    chi
    0.97
    hazard
    0.96
    zza
    0.95
    ppa
    0.95
    Activations Density 12.161%

    No Known Activations