© 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. 0-RES-JB
    11. 6755
    Prev
    Next
    INDEX
    Explanations

    special characters that are not typical in the English language

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols that may indicate formatting or punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     grips
    -0.74
     catch
    -0.69
     comp
    -0.66
     Chargers
    -0.66
     Bott
    -0.65
     order
    -0.63
     PS
    -0.63
     flash
    -0.61
     Targ
    -0.61
     GTA
    -0.61
    POSITIVE LOGITS
    ¶
    4.50
    ¶æ
    2.57
    ·
    2.07
    ³
    1.93
    µ
    1.92
    ¸
    1.90
    ¹
    1.87
    ´
    1.83
    º
    1.80
    °
    1.79
    Activations Density 0.009%

    No Known Activations