© 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. 1982
    Prev
    Next
    INDEX
    Explanations

    words related to fictional elements or settings

    oai_token-act-pair · gpt-3.5-turbo

    mentions of fictional elements or characters in various contexts

    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
    ktop
    -0.89
    hammad
    -0.74
    ni
    -0.73
    pour
    -0.73
    ereo
    -0.71
    acks
    -0.71
    wick
    -0.69
    chains
    -0.69
    artney
    -0.69
    olen
    -0.68
    POSITIVE LOGITS
    ized
    1.11
    izations
    0.97
    ties
    0.95
    ization
    0.94
    izable
    0.93
    ised
    0.93
    IZ
    0.91
    istically
    0.90
     universes
    0.90
    isation
    0.89
    Activations Density 0.045%

    No Known Activations