© 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. 4-RES-JB
    11. 3679
    Prev
    Next
    INDEX
    Explanations

    names related to a specific filmmaker

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual or entity

    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
     secession
    -0.65
     Lobby
    -0.65
     bleach
    -0.65
     clerks
    -0.63
     delusional
    -0.62
     dividend
    -0.62
     Concord
    -0.62
     MFT
    -0.62
     turnout
    -0.62
     propagation
    -0.61
    POSITIVE LOGITS
    oj
    1.20
    unction
    1.13
    itsu
    1.10
    ournals
    1.10
    ihad
    0.96
    ournal
    0.96
    ames
    0.96
    acket
    0.96
    unal
    0.95
    ean
    0.95
    Activations Density 0.006%

    No Known Activations