© 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. 17271
    Prev
    Next
    INDEX
    Explanations

    Cyrillic characters with associated Latin characters, potentially indicating a pattern in a specific language

    oai_token-act-pair · gpt-3.5-turbo

    foreign characters or symbols typically used in non-English scripts

    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
     Riley
    -0.82
     panels
    -0.63
     Kansas
    -0.60
     shocks
    -0.60
     specificity
    -0.59
     springs
    -0.58
     Blossom
    -0.58
     transports
    -0.58
     Advent
    -0.58
     KS
    -0.57
    POSITIVE LOGITS
    оÐ
    1.85
    ÑĢ
    1.85
    Ñĥ
    1.79
    л
    1.77
    а
    1.74
    е
    1.74
    о
    1.70
    Ñĭ
    1.63
    и
    1.61
    в
    1.59
    Activations Density 0.023%

    No Known Activations