© 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. 1-RES-JB
    11. 16445
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals or entities, potentially within a specific context

    oai_token-act-pair · gpt-3.5-turbo

    names of notable individuals, particularly those related to specific events or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     civilized
    -0.68
    ifier
    -0.67
    ften
    -0.63
    semble
    -0.63
    ¤
    -0.61
     Valve
    -0.60
    н
    -0.59
     Nordic
    -0.59
    ter
    -0.58
    comes
    -0.58
    POSITIVE LOGITS
     Fitzgerald
    1.38
    gerald
    1.13
    olini
    0.91
     Gallagher
    0.77
    sonian
    0.77
    weed
    0.76
    haus
    0.75
     Stout
    0.72
    avorite
    0.72
    allery
    0.70
    Activations Density 0.005%

    No Known Activations