© 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. 8-RES-JB
    11. 20251
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing detailed instructions or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to regulations and compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sculpt
    -0.78
     frontline
    -0.77
     thrill
    -0.75
     raft
    -0.73
     rive
    -0.71
     tackling
    -0.71
     spir
    -0.71
     thrilled
    -0.71
     casc
    -0.70
     Blair
    -0.70
    POSITIVE LOGITS
    Example
    1.63
    Examples
    1.60
    References
    1.54
    Methods
    1.47
    Types
    1.44
    Trivia
    1.44
    If
    1.43
    Information
    1.42
    Discussion
    1.41
    Note
    1.39
    Activations Density 0.375%

    No Known Activations