© 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. 15063
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to various fields

    oai_token-act-pair · gpt-3.5-turbo

    terms related to scientific or technical processes and components

    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
    ãĤ¨ãĥ«
    -0.64
    GAN
    -0.52
    INAL
    -0.52
    ãĥ´
    -0.51
    ãĥį
    -0.51
    yss
    -0.51
    é¾įå
    -0.50
    ãĥĥãĥī
    -0.50
    æĢ
    -0.48
    ABLE
    -0.46
    POSITIVE LOGITS
    hips
    0.98
    hops
    0.93
    mith
    0.83
    hip
    0.81
    etting
    0.81
    paces
    0.80
    ettings
    0.80
    uggest
    0.79
    ynthesis
    0.75
    uits
    0.74
    Activations Density 1.074%

    No Known Activations