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. 9-RES-JB
    6. 22599
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers separated by symbols like hyphens or slashes

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and specific codes or identifiers

    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
    mos
    -0.73
    Interested
    -0.72
    NC
    -0.71
    IFT
    -0.70
    MU
    -0.69
    Nap
    -0.66
    maxwell
    -0.65
    cius
    -0.65
    Radio
    -0.65
    SCP
    -0.65
    POSITIVE LOGITS
    cffff
    0.71
     carriage
    0.66
     accur
    0.64
     complying
    0.61
     portrayal
    0.60
     servants
    0.59
     adequ
    0.58
    escription
    0.57
     Devi
    0.57
     gard
    0.57
    Activations Density 0.074%

    No Known Activations