© 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. 19956
    Prev
    Next
    INDEX
    Explanations

    terms related to separation or division

    oai_token-act-pair · gpt-3.5-turbo

    terms related to separation or division

    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
    inel
    -0.90
    psc
    -0.88
    anamo
    -0.79
    odium
    -0.75
    aina
    -0.72
    enez
    -0.72
    kinson
    -0.71
    kson
    -0.70
    azor
    -0.69
    lev
    -0.69
    POSITIVE LOGITS
     partition
    1.08
     partitions
    1.06
     Tsukuyomi
    0.78
     divid
    0.77
    ãĥ¼ãĥĨ
    0.75
    ipation
    0.74
     flares
    0.74
    naire
    0.73
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.72
     ãĤµ
    0.71
    Activations Density 0.009%

    No Known Activations