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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 12836
    Prev
    Next
    INDEX
    Explanations

    references to specific episodes of a TV series

    oai_token-act-pair · gpt-3.5-turbo

    references to specific television episodes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ntil
    -0.78
    fman
    -0.76
    sheet
    -0.70
    umbai
    -0.70
    punk
    -0.70
    sheets
    -0.69
    hari
    -0.69
    artisan
    -0.69
    ndum
    -0.68
    uckland
    -0.67
    POSITIVE LOGITS
     aired
    1.07
     airing
    0.96
     finale
    0.95
     episode
    0.90
     airs
    0.90
     premiere
    0.89
     episodes
    0.87
     premie
    0.87
     opener
    0.87
    ĸļ
    0.86
    Activations Density 0.034%

    No Known Activations