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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 4-RES-JB
    6. 8825
    Prev
    Next
    INDEX
    Explanations

    specific mentions of locations and organizations, particularly related to FDNY (Fire Department of New York) and Valencia

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Federal Deposit Insurance Corporation and related financial topics

    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
    asure
    -0.76
    ffield
    -0.75
    icles
    -0.75
    suit
    -0.75
    etus
    -0.74
    fters
    -0.73
    apore
    -0.72
    etition
    -0.71
    icit
    -0.71
    pload
    -0.71
    POSITIVE LOGITS
     FD
    0.86
     Valencia
    0.80
    FD
    0.77
    vation
    0.74
    Pont
    0.69
     Bread
    0.67
    acci
    0.66
    RGB
    0.65
    ible
    0.64
     FSA
    0.64
    Activations Density 0.033%

    No Known Activations