© 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 EvalsExportsinterp-engineNEWAPI 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. 11468
    Prev
    Next
    INDEX
    Explanations

    phrases related to processes involving disposal, transportation, or movement of objects

    oai_token-act-pair · gpt-3.5-turbo

    references to harmful behaviors or substances

    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
    STEM
    -0.69
    STRUCT
    -0.65
     Adren
    -0.64
    define
    -0.64
     Belief
    -0.62
    DEM
    -0.62
     Intervention
    -0.61
     Discipline
    -0.60
    era
    -0.59
     fasc
    -0.59
    POSITIVE LOGITS
     deposited
    1.29
     spilled
    1.15
     stored
    1.12
     redistributed
    1.11
     dispersed
    1.09
     smuggled
    1.08
     collected
    1.06
     accumulated
    1.02
     transmitted
    1.01
     transferred
    1.01
    Activations Density 1.379%

    No Known Activations