© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 2745
    Prev
    Next
    INDEX
    Explanations

    numeric values or mathematical symbols within a text

    oai_token-act-pair · gpt-3.5-turbo

    symbols and punctuation related to statistical or financial information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gors
    -0.70
     Constantin
    -0.68
     Hoo
    -0.68
     Frie
    -0.65
     Franch
    -0.63
     Mills
    -0.63
     Hindu
    -0.63
     Nguyen
    -0.61
     Chong
    -0.61
     Franco
    -0.60
    POSITIVE LOGITS
    >)
    1.05
    )!
    0.91
    )/
    0.89
    tnc
    0.88
    )[
    0.85
    /-
    0.85
    ?),
    0.84
    wcsstore
    0.83
    ?).
    0.83
    )...
    0.83
    Activations Density 0.055%

    No Known Activations