© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 7178
    Prev
    Next
    INDEX
    Explanations

    terms related to malt

    oai_token-act-pair · gpt-3.5-turbo

    terms related to brewing and malt ingredients

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

    No Comments

    Negative Logits
    esome
    -0.82
    asso
    -0.77
    apo
    -0.76
    acco
    -0.74
    entin
    -0.73
    aukee
    -0.73
    lli
    -0.71
    ppard
    -0.70
    ndra
    -0.68
    llan
    -0.67
    POSITIVE LOGITS
    NF
    0.85
    ãĥĥãĥī
    0.84
    ependent
    0.79
    200000
    0.78
    Bay
    0.70
    Ĥ¬
    0.70
    epend
    0.70
    ãĥį
    0.67
    ãĥ¯ãĥ³
    0.66
    osc
    0.66
    Activations Density 0.012%

    No Known Activations