© 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. 9-RES-JB
    11. 5358
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific actions or commands

    oai_token-act-pair · gpt-3.5-turbo

    references to summoning or characteristics of monsters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hner
    -0.72
    Ń
    -0.70
    iferation
    -0.68
    rarily
    -0.68
    ĸļ
    -0.64
    ãĤ¸
    -0.64
    ishops
    -0.64
    obbies
    -0.64
    atform
    -0.63
    ł
    -0.62
    POSITIVE LOGITS
     .)
    0.83
    and
    0.79
     ,
    0.73
     signifies
    0.72
     ."
    0.71
     ,"
    0.70
    within
    0.66
     SEE
    0.66
     ).
    0.66
     âĸ
    0.66
    Activations Density 0.079%

    No Known Activations