© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 6874
    Prev
    Next
    INDEX
    Explanations

    dates in a day-month format

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of specific numerical sequences or scores in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "$:/
    -0.73
     Bates
    -0.72
     wedd
    -0.68
     fifty
    -0.65
     Sidd
    -0.62
     validation
    -0.61
     plagued
    -0.60
     ().
    -0.60
     Stub
    -0.57
     Lenn
    -0.57
    POSITIVE LOGITS
    minute
    0.96
    sided
    0.96
    year
    0.91
    liter
    0.91
    inch
    0.90
    0
    0.90
    day
    0.90
    degree
    0.89
    point
    0.89
    digit
    0.88
    Activations Density 0.092%

    No Known Activations