© 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. 1766
    Prev
    Next
    INDEX
    Explanations

    numbers written out in words

    oai_token-act-pair · gpt-3.5-turbo
    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
    ãĤ¯
    -0.89
    isSpecialOrderable
    -0.73
    ãĤ¼ãĤ¦ãĤ¹
    -0.67
     QR
    -0.67
    ivities
    -0.63
    ãĤ±
    -0.63
    ãĥĨ
    -0.63
    ãĥIJ
    -0.63
    ãĥ¬
    -0.63
    ãĤ¨ãĥ«
    -0.63
    POSITIVE LOGITS
     thousand
    0.82
    ths
    0.76
    teen
    0.73
    eenth
    0.73
    eight
    0.72
     hundred
    0.69
    tarian
    0.68
     dozen
    0.68
    awatts
    0.66
    ousand
    0.66
    Activations Density 0.106%

    No Known Activations