© 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. 4-RES-JB
    11. 6710
    Prev
    Next
    INDEX
    Explanations

    dollar signs and mathematical symbols

    oai_token-act-pair · gpt-3.5-turbo

    monetary values or financial symbols

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

    No Comments

    Negative Logits
    ock
    -0.88
    reet
    -0.80
    oke
    -0.70
    icult
    -0.67
    igi
    -0.65
    Bul
    -0.62
    jas
    -0.61
     Breed
    -0.60
     Yel
    -0.60
    isan
    -0.59
    POSITIVE LOGITS
    frac
    0.99
     $\
    0.88
    {\
    0.87
    $.
    0.85
    href
    0.83
    dyl
    0.81
    $$
    0.80
    {{
    0.79
    endif
    0.72
    surface
    0.72
    Activations Density 0.011%

    No Known Activations