Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 21333
    Prev
    Next
    INDEX
    Explanations

    terms related to different human species, particularly Homo species

    oai_token-act-pair · gpt-3.5-turbo

    terms related to human evolution and taxonomy

    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
    OHN
    -0.77
    pecially
    -0.72
    NESS
    -0.70
    fax
    -0.70
    ensing
    -0.70
    RH
    -0.69
    isters
    -0.69
    irtual
    -0.68
    ARS
    -0.66
    ãĥ´ãĤ¡
    -0.64
    POSITIVE LOGITS
    thal
    1.32
     Neander
    0.88
    zee
    0.86
    zees
    0.81
    olithic
    0.80
     tribes
    0.76
    istani
    0.73
    osaurus
    0.73
     Homo
    0.72
    ocene
    0.71
    Activations Density 0.014%

    No Known Activations