Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 19724
    Prev
    Next
    INDEX
    Explanations

    single characters

    oai_token-act-pair · gpt-3.5-turbo

    unique characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ufact
    -1.09
    merce
    -0.90
     ethic
    -0.83
    psey
    -0.83
     carbohyd
    -0.82
    raviolet
    -0.81
     synerg
    -0.80
     volunte
    -0.79
    wcs
    -0.78
    secut
    -0.76
    POSITIVE LOGITS
    Ī
    1.18
    Ĩ
    1.18
    ĩ
    1.04
    ÃįÃį
    1.03
    ãĤĭ
    0.97
    Ĺ
    0.96
    ãĥĺ
    0.96
    ÙĦ
    0.94
    е
    0.93
    İ
    0.93
    Activations Density 0.003%

    No Known Activations