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. 9-RES-JB
    6. 6517
    Prev
    Next
    INDEX
    Explanations

    declarations or introductions to emphasize or confirm statements

    oai_token-act-pair · gpt-3.5-turbo

    expressions of acknowledgment or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urger
    -0.71
     brim
    -0.67
    string
    -0.66
    strings
    -0.63
    graph
    -0.60
    chet
    -0.60
    stal
    -0.60
    sov
    -0.59
    uded
    -0.59
    minecraft
    -0.58
    POSITIVE LOGITS
    lahoma
    1.24
    AY
    1.19
     bye
    0.92
    awaru
    0.90
    Okay
    0.88
    Alright
    0.75
     OK
    0.75
     folks
    0.75
    OK
    0.74
    ratulations
    0.73
    Activations Density 0.025%

    No Known Activations