© 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. 10-RES-JB
    11. 11405
    Prev
    Next
    INDEX
    Explanations

    latinate vocabulary and formal language

    oai_token-act-pair · gpt-3.5-turbo

    elements of film critique, particularly regarding symbolism and thematic depth

    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
    unicip
    -0.84
    igslist
    -0.77
    Federal
    -0.75
    incial
    -0.75
    reprene
    -0.75
    QB
    -0.74
    Hispanic
    -0.74
     mathemat
    -0.74
    Republican
    -0.73
    ollah
    -0.73
    POSITIVE LOGITS
     Whedon
    1.10
     Gone
    1.07
     Suicide
    1.00
     Clockwork
    0.99
     Tales
    0.99
     Nolan
    0.98
     Ghost
    0.97
     Firefly
    0.97
     sequels
    0.96
     Reign
    0.96
    Activations Density 0.719%

    No Known Activations