© 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. 2-RES-JB
    11. 13035
    Prev
    Next
    INDEX
    Explanations

    technical terms or jargon

    oai_token-act-pair · gpt-3.5-turbo

    symbols or punctuation marks that denote lists or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jriwal
    -0.82
    ied
    -0.76
    enhagen
    -0.74
    eeds
    -0.74
    ikuman
    -0.73
    ipeg
    -0.72
    chwitz
    -0.72
    akuya
    -0.68
    unk
    -0.68
    olk
    -0.67
    POSITIVE LOGITS
    ··
    0.87
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.82
     ·
    0.81
    lins
    0.80
    nery
    0.74
     RL
    0.71
    glers
    0.70
    IRO
    0.70
    nes
    0.69
     Jol
    0.69
    Activations Density 0.025%

    No Known Activations