© 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. 3-RES-JB
    11. 15126
    Prev
    Next
    INDEX
    Explanations

    prices or costs mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    monetary values or prices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tall
    -0.80
     Nare
    -0.80
     Pru
    -0.78
     guid
    -0.77
     exerc
    -0.75
    umbn
    -0.74
     Bere
    -0.71
     Slov
    -0.71
     Gors
    -0.69
     Samar
    -0.68
    POSITIVE LOGITS
    $$
    1.23
    $$$$
    1.20
    HOME
    0.96
    -$
    0.93
    USD
    0.93
    100
    0.92
    $
    0.91
    AUD
    0.89
    200
    0.88
    false
    0.88
    Activations Density 0.080%

    No Known Activations