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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-RES-JB
    6. 4288
    Prev
    Next
    INDEX
    Explanations

    names, especially those of Eastern European origin

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals, particularly those involved in creative or impactful roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.86
    TAIN
    -0.79
    éļ
    -0.76
     Failure
    -0.74
    OTAL
    -0.71
    lement
    -0.70
     Participation
    -0.68
    ACTED
    -0.67
    rollment
    -0.67
    ancial
    -0.64
    POSITIVE LOGITS
    amaz
    0.80
     Kaz
    0.77
    iggurat
    0.75
    onis
    0.74
    orb
    0.73
    imir
    0.73
    oan
    0.72
    imoto
    0.72
    uki
    0.72
    hur
    0.72
    Activations Density 0.022%

    No Known Activations