© 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. 9-RES-JB
    11. 1988
    Prev
    Next
    INDEX
    Explanations

    directives to provide information or recount stories

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve narration or storytelling

    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
    imposed
    -0.70
    nam
    -0.69
    isk
    -0.67
    adesh
    -0.66
    cells
    -0.65
    ccording
    -0.62
    everal
    -0.61
    berus
    -0.61
    aband
    -0.61
     notor
    -0.61
    POSITIVE LOGITS
    tale
    1.58
     tales
    1.05
    ingly
    1.05
     stories
    1.02
     us
    1.00
     tale
    0.98
     lies
    0.92
     Stories
    0.88
     Tale
    0.87
     me
    0.83
    Activations Density 0.062%

    No Known Activations