© 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. 2-RES-JB
    11. 9299
    Prev
    Next
    INDEX
    Explanations

    numeric values within a technical context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "value" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spread
    -0.73
    riad
    -0.72
    chu
    -0.71
    tiny
    -0.70
    ned
    -0.66
     Eye
    -0.66
    thumbnails
    -0.66
    wordpress
    -0.65
    creen
    -0.65
     tongues
    -0.65
    POSITIVE LOGITS
     value
    0.89
     values
    0.87
    =\"
    0.81
    EStream
    0.81
    value
    0.78
    values
    0.72
     Values
    0.71
    VALUE
    0.70
     Value
    0.69
    Values
    0.69
    Activations Density 0.013%

    No Known Activations