© 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. 1057
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions or events that have implications or consequences

    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
    ????
    -0.58
    !]
    -0.57
    inav
    -0.57
    ?,
    -0.57
    âĢ¦]
    -0.57
    ...)
    -0.55
     USA
    -0.55
    )!
    -0.55
     *)
    -0.54
     Analy
    -0.54
    POSITIVE LOGITS
    ĸļ
    1.00
    often
    0.86
    sometimes
    0.81
    particularly
    0.79
    entimes
    0.73
    Often
    0.70
    NetMessage
    0.70
    asionally
    0.69
    ãĤ¦ãĤ¹
    0.69
    efully
    0.68
    Activations Density 0.980%

    No Known Activations