© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 22862
    Prev
    Next
    INDEX
    Explanations

    verbs indicating action or processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions and efforts toward goals or tasks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¢
    -0.70
    misc
    -0.70
    illegal
    -0.68
    Ļ½
    -0.64
    querque
    -0.64
    vol
    -0.63
    amon
    -0.62
    ãĤ±
    -0.62
    found
    -0.62
    osate
    -0.61
    POSITIVE LOGITS
     progresses
    0.97
     unfolds
    0.91
     prepares
    0.85
     progressed
    0.83
     increasingly
    0.75
     fades
    0.74
     progressively
    0.74
     consolid
    0.73
     transitioned
    0.72
     evolves
    0.72
    Activations Density 0.221%

    No Known Activations