© 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. 15200
    Prev
    Next
    INDEX
    Explanations

    dates expressed in years

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years

    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
    ype
    -0.69
    ynchron
    -0.64
    amines
    -0.62
     hypocr
    -0.62
    amins
    -0.61
    idine
    -0.60
    EStreamFrame
    -0.60
    hing
    -0.59
    illin
    -0.58
    undown
    -0.57
    POSITIVE LOGITS
    -'
    0.95
    å¹
    0.88
     onwards
    0.78
    bard
    0.75
    borg
    0.74
    ãĥ¼ãĥ«
    0.69
    ruary
    0.67
    fair
    0.67
     BCE
    0.65
    foundland
    0.63
    Activations Density 0.146%

    No Known Activations