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. 7-RES-JB
    6. 15780
    Prev
    Next
    INDEX
    Explanations

    phrases related to qualities of things or people, being well-regarded, deserving, tempered, or dressed

    oai_token-act-pair · gpt-3.5-turbo

    words that indicate various states or conditions of being well-sourced or well-managed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wolves
    -0.78
    UA
    -0.71
    wolf
    -0.70
    MEN
    -0.69
    knife
    -0.66
    mania
    -0.63
    terms
    -0.60
    Fra
    -0.60
    particip
    -0.60
    shall
    -0.60
    POSITIVE LOGITS
    tenance
    0.94
    ceived
    0.87
    anced
    0.79
    vised
    0.78
    enged
    0.77
    nered
    0.77
    ileged
    0.77
    orted
    0.75
    angled
    0.73
    aund
    0.71
    Activations Density 0.098%

    No Known Activations