© 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. 1-RES-JB
    11. 3641
    Prev
    Next
    INDEX
    Explanations

    keywords related to evolutionary biology

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to evolution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zzle
    -0.82
    EMA
    -0.79
    epad
    -0.79
    GV
    -0.76
    ryn
    -0.75
    maid
    -0.73
    vr
    -0.73
    rain
    -0.72
    zos
    -0.72
    zz
    -0.72
    POSITIVE LOGITS
     biologist
    1.15
     biology
    1.06
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    1.06
     evolutionary
    1.05
     biologists
    0.99
    ĸļ
    0.85
     evolution
    0.83
     theoret
    0.81
     ecology
    0.79
     organisms
    0.77
    Activations Density 0.006%

    No Known Activations