© 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. 4-RES-JB
    11. 893
    Prev
    Next
    INDEX
    Explanations

    phrases related to film sets

    oai_token-act-pair · gpt-3.5-turbo

    references to film sets and their characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -0.83
    aud
    -0.69
     ILCS
    -0.66
    ibly
    -0.65
    ishable
    -0.63
    pecially
    -0.62
    asive
    -0.62
    eous
    -0.61
    ishy
    -0.61
    ished
    -0.60
    POSITIVE LOGITS
    tle
    0.95
    list
    0.86
    rac
    0.85
    offs
    0.82
    opsis
    0.76
     abl
    0.74
     showc
    0.74
    piece
    0.73
    ropolis
    0.73
    ters
    0.72
    Activations Density 0.036%

    No Known Activations