© 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. 4-RES-JB
    6. 2892
    Prev
    Next
    INDEX
    Explanations

    proper nouns of names

    oai_token-act-pair · gpt-3.5-turbo

    names of places and people, particularly related to Devon and individuals named Donna

    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
    ¶æ
    -0.85
    eering
    -0.84
    inventoryQuantity
    -0.82
    heit
    -0.80
    lines
    -0.78
    otle
    -0.78
    ues
    -0.75
    ambo
    -0.72
    undo
    -0.72
    thumbnails
    -0.71
    POSITIVE LOGITS
     Bride
    0.84
    idia
    0.79
    ciples
    0.78
    iver
    0.76
    aimon
    0.75
    imon
    0.72
    ILS
    0.71
    ise
    0.69
    âĶĢâĶĢ
    0.67
     Harmon
    0.67
    Activations Density 0.029%

    No Known Activations