© 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. 15221
    Prev
    Next
    INDEX
    Explanations

    proper names followed by "himself."

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals in a self-referential context

    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
    olid
    -0.88
    okin
    -0.71
    CLOSE
    -0.71
    MSN
    -0.70
    ulton
    -0.68
     Conversation
    -0.67
    ayne
    -0.67
    urry
    -0.66
    ONES
    -0.66
    microsoft
    -0.65
    POSITIVE LOGITS
    ortium
    0.78
     profess
    0.73
     contradicted
    0.73
     proport
    0.73
     predec
    0.71
     confessed
    0.71
     doct
    0.71
     greets
    0.70
     hars
    0.70
     conclud
    0.67
    Activations Density 0.040%

    No Known Activations