© 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. 2-RES-JB
    6. 2480
    Prev
    Next
    INDEX
    Explanations

    suggestions or recommendations in sentences

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a proposal or assertion

    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
    tal
    -0.78
    ccording
    -0.77
    dig
    -0.72
    cod
    -0.68
    vin
    -0.67
    fare
    -0.64
    EStreamFrame
    -0.64
    woods
    -0.63
    aliation
    -0.63
     ali
    -0.61
    POSITIVE LOGITS
     suggestions
    0.83
    ible
    0.83
    kinson
    0.73
    suggest
    0.71
    ibility
    0.71
    ively
    0.70
    ered
    0.70
    uggest
    0.70
    herty
    0.70
     suggesting
    0.69
    Activations Density 0.034%

    No Known Activations