© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 12409
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences involving actions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe actions or processes

    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
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.68
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.67
    ipe
    -0.67
    \\\\\\\\\\\\\\\\
    -0.67
     skies
    -0.66
    century
    -0.63
    onew
    -0.61
    apult
    -0.60
    Ö¼
    -0.60
     Floating
    -0.58
    POSITIVE LOGITS
    licts
    0.82
    itaire
    0.80
    ioned
    0.76
    ulkan
    0.75
     involve
    0.73
    ments
    0.72
    untarily
    0.69
     Deity
    0.69
    =#
    0.68
    qv
    0.67
    Activations Density 0.021%

    No Known Activations