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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 9136
    Prev
    Next
    INDEX
    Explanations

    the phrase "bona fide", and potentially words related to authenticity or validation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to authenticity and credibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sg
    -0.91
    trap
    -0.73
    notes
    -0.73
    lace
    -0.69
    nir
    -0.69
    dress
    -0.69
    loss
    -0.68
    nesium
    -0.68
    nan
    -0.67
    meyer
    -0.66
    POSITIVE LOGITS
     fide
    1.50
     bona
    1.08
    ignt
    0.91
    zona
    0.85
    ça
    0.84
    ignty
    0.80
    veyard
    0.80
    BILITIES
    0.80
    BILITY
    0.79
    Ãĥ
    0.79
    Activations Density 0.025%

    No Known Activations