© 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. 20274
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions of closing or ceasing operations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "shut down" and related references to shutdowns in various contexts

    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
    OD
    -0.76
     Drawn
    -0.72
    present
    -0.72
    Catalog
    -0.68
    ry
    -0.68
    yne
    -0.65
    umper
    -0.64
    rouse
    -0.64
    orthy
    -0.63
    MAT
    -0.62
    POSITIVE LOGITS
     abruptly
    0.83
    escent
    0.79
     doors
    0.78
     runaway
    0.76
    river
    0.75
     highways
    0.75
     valves
    0.73
     hostilities
    0.72
     freeway
    0.71
    grading
    0.70
    Activations Density 0.063%

    No Known Activations