© 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. 10203
    Prev
    Next
    INDEX
    Explanations

    words related to legal or political issues, specifically centered around a person named "Jadhav" and the concept of a dashboard

    oai_token-act-pair · gpt-3.5-turbo

    elements related to a specific person's name and associated contexts

    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
    edIn
    -0.82
    Ĩ
    -0.76
    ij士
    -0.76
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.75
    zeb
    -0.73
    YL
    -0.73
    eur
    -0.71
    yg
    -0.70
    sets
    -0.70
    ebus
    -0.70
    POSITIVE LOGITS
    uckle
    0.91
    idy
    0.80
    boro
    0.77
    mitter
    0.75
    uckles
    0.74
    ivery
    0.74
    borough
    0.71
    apter
    0.69
    igan
    0.69
     shuffle
    0.68
    Activations Density 0.036%

    No Known Activations