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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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 E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 13930
    Prev
    Next
    INDEX
    Explanations

    mentions of specific food items such as peanuts, rice, coconut, and cannabis

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    +0.22
    0.9%
    326
    +0.18
    0.7%
    461
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.22
    0.20
    461
    +0.18
    0.14
    481
    +0.14
    0.18
    Negative Logits
    utm
    -0.91
    /_
    -0.87
     Jah
    -0.86
    ãĥĥãĥĪ
    -0.85
    ×Ļ×
    -0.83
     Katy
    -0.82
     EMS
    -0.82
    ++++++++++++++++
    -0.82
    ],[
    -0.80
    hig
    -0.77
    POSITIVE LOGITS
     lovers
    1.03
     lover
    0.96
     themed
    0.91
     enthusiasts
    0.90
     enthusiast
    0.83
     indic
    0.82
     simulator
    0.79
     terminology
    0.77
     cubes
    0.77
    schild
    0.77
    Activations Density 2.892%

    No Known Activations