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. 6-RES-JB
    6. 13373
    Prev
    Next
    INDEX
    Explanations

    words related to configurations or structures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to analysis and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     channels
    -0.57
    cest
    -0.56
    apeake
    -0.56
     Scouts
    -0.55
    ighters
    -0.55
    ongs
    -0.54
    itters
    -0.54
    events
    -0.53
    apest
    -0.53
    ammers
    -0.53
    POSITIVE LOGITS
     consisting
    0.80
     whereby
    0.72
     involving
    0.69
     akin
    0.67
     wherein
    0.67
    DragonMagazine
    0.63
     showcasing
    0.62
     resembling
    0.62
     reminiscent
    0.61
     titled
    0.59
    Activations Density 0.536%

    No Known Activations