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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4614
    Prev
    Next
    INDEX
    Explanations

    names of places

    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
    0.9%
    481
    +0.15
    0.6%
    764
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.22
    0.28
    481
    +0.15
    0.26
    367
    +0.12
    0.16
    Negative Logits
    apego
    -0.98
    umbnails
    -0.83
    hement
    -0.81
    ournal
    -0.80
    rogens
    -0.79
    vantage
    -0.77
    quished
    -0.76
    acebook
    -0.74
    hler
    -0.74
    yip
    -0.73
    POSITIVE LOGITS
     guise
    1.21
     mode
    1.08
     contexts
    1.05
     manner
    0.99
     context
    0.97
     circles
    0.96
     vicinity
    0.93
     fashion
    0.87
     territory
    0.87
     increments
    0.85
    Activations Density 11.800%

    No Known Activations