© 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. 9963
    Prev
    Next
    INDEX
    Explanations

    the character "Ċ"

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical or date-related information in a news context

    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
     newsp
    -0.68
     oun
    -0.65
     newcom
    -0.60
     simul
    -0.58
     exha
    -0.58
     Bridges
    -0.57
     Princ
    -0.54
     contemplation
    -0.54
     Crab
    -0.54
     councill
    -0.54
    POSITIVE LOGITS
    IPP
    0.70
    使
    0.65
    TY
    0.63
    328
    0.63
    Islamic
    0.62
    GER
    0.62
    Turkish
    0.62
    African
    0.62
    Philipp
    0.61
    BR
    0.61
    Activations Density 0.088%

    No Known Activations