© 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. 1-RES-JB
    11. 20062
    Prev
    Next
    INDEX
    Explanations

    numbers related to quantities or measurements

    oai_token-act-pair · gpt-3.5-turbo

    numbers associated with various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    folk
    -0.84
    âĹ¼
    -0.82
    gets
    -0.74
    holder
    -0.71
    hold
    -0.70
    holders
    -0.69
    Glass
    -0.69
    holding
    -0.68
    flush
    -0.68
     RTX
    -0.67
    POSITIVE LOGITS
    %:
    0.98
    80
    0.92
    90
    0.90
     94
    0.87
    ¢
    0.86
     mph
    0.84
     dB
    0.84
     93
    0.82
     92
    0.81
    803
    0.77
    Activations Density 0.033%

    No Known Activations