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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 19360
    Prev
    Next
    INDEX
    Explanations

    information related to sports seasons and performances

    oai_token-act-pair · gpt-3.5-turbo

    references to the completion and details of a sports season

    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
     persisted
    -0.71
     persists
    -0.64
     ongoing
    -0.64
     recent
    -0.59
    lations
    -0.58
    ritten
    -0.57
     Matter
    -0.57
     Frequ
    -0.57
     manifests
    -0.56
    ication
    -0.56
    POSITIVE LOGITS
     knowing
    0.94
     expecting
    0.93
     intending
    0.88
     cautiously
    0.84
     prematurely
    0.84
     undefeated
    0.83
     differently
    0.82
     WITHOUT
    0.78
     believing
    0.78
     unsc
    0.77
    Activations Density 0.275%

    No Known Activations