© 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. 11-RES-JB
    11. 24056
    Prev
    Next
    INDEX
    Explanations

    statistics or numerical figures

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to statistics and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UGC
    -0.66
    icho
    -0.65
     Certain
    -0.64
     Firstly
    -0.61
     Reboot
    -0.61
     SHARES
    -0.60
    é¾įå¥ij士
    -0.60
     playbook
    -0.57
    Certain
    -0.57
    ovember
    -0.56
    POSITIVE LOGITS
     theirs
    0.99
     only
    0.88
     whopping
    0.82
     averages
    0.81
     barely
    0.80
     langu
    0.78
     hers
    0.78
     likewise
    0.77
     meas
    0.76
    only
    0.76
    Activations Density 0.261%

    No Known Activations