© 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
    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. 5106
    Prev
    Next
    INDEX
    Explanations

    references to quantities or measures

    oai_token-act-pair · gpt-3.5-turbo

    references to quantities and measures

    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
    helm
    -0.83
    arna
    -0.82
    INA
    -0.79
    inka
    -0.74
    warts
    -0.72
    ̶
    -0.69
    Blade
    -0.68
    NetMessage
    -0.67
    OTA
    -0.67
    ilver
    -0.67
    POSITIVE LOGITS
     amount
    0.87
     allowable
    0.85
    liest
    0.82
     closest
    0.75
     equivalent
    0.73
     number
    0.72
     extent
    0.72
     amounts
    0.68
     difference
    0.68
     of
    0.67
    Activations Density 0.208%

    No Known Activations