© 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. 7078
    Prev
    Next
    INDEX
    Explanations

    Slavic characters and text, potentially related to a specific language or encoding

    oai_token-act-pair · gpt-3.5-turbo
    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
     counterpart
    -0.64
     forth
    -0.62
     Sporting
    -0.61
     WARN
    -0.60
     plans
    -0.59
     McCann
    -0.58
     scrutin
    -0.58
     boldly
    -0.57
     receivers
    -0.57
     Know
    -0.57
    POSITIVE LOGITS
    ħ
    2.12
    ĩ
    2.10
    Ĩ
    2.06
    İ
    2.00
    Ī
    1.96
    ī
    1.91
    Ĭ
    1.83
    Ħ
    1.79
    į
    1.77
    ĸ
    1.67
    Activations Density 0.021%

    No Known Activations