© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 4467
    Prev
    Next
    INDEX
    Explanations

    comparisons or contrasts between different entities or values

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving comparisons or relative terms

    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
    icious
    -0.73
    */(
    -0.71
    ANCE
    -0.70
    Wr
    -0.66
    ainer
    -0.65
    Sym
    -0.65
     Inquiry
    -0.64
    Nat
    -0.62
    erto
    -0.62
    OA
    -0.60
    POSITIVE LOGITS
     ours
    0.78
     favorably
    0.73
    whelming
    0.68
     afar
    0.67
     comparable
    0.66
     baseline
    0.65
    rast
    0.64
     previous
    0.64
    stellar
    0.61
     Tsukuyomi
    0.61
    Activations Density 0.080%

    No Known Activations