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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 9677
    Prev
    Next
    INDEX
    Explanations

    numerical values indicating records, achievements, or statistical highs, particularly in sports

    oai_token-act-pair · gpt-3.5-turbo
    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
    mass
    -0.77
     Mandal
    -0.77
    xxx
    -0.75
    pring
    -0.73
     ®
    -0.72
    Band
    -0.71
    intel
    -0.71
    mod
    -0.70
    indust
    -0.70
    ites
    -0.68
    POSITIVE LOGITS
    LEASE
    0.83
     goaltender
    0.77
     record
    0.74
     scorer
    0.73
     tally
    0.71
     haul
    0.69
     sixth
    0.68
     whopping
    0.67
     eighth
    0.67
     waiver
    0.67
    Activations Density 0.105%

    No Known Activations