© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 4057
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "man" as part of a broader term

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and identifiers, often related to specific characters or names in cultural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStreamFrame
    -0.82
    externalActionCode
    -0.73
    inventoryQuantity
    -0.73
    ĪĴ
    -0.73
    ====
    -0.71
    bda
    -0.70
    RGB
    -0.70
    ets
    -0.70
    cffff
    -0.70
     CrossRef
    -0.69
    POSITIVE LOGITS
    man
    1.63
    MAN
    1.41
    mans
    1.40
    Man
    1.25
     Man
    1.21
    men
    1.18
     MAN
    1.15
     man
    1.08
    mann
    1.05
    woman
    1.00
    Activations Density 0.216%

    No Known Activations