© 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. 6-RES-JB
    11. 11611
    Prev
    Next
    INDEX
    Explanations

    terms related to the theory of evolution, including evolution, selection, evolutionary biology, ancestor, and fossils

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to evolution and evolutionary theory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Territories
    -0.71
    åĤ
    -0.70
    stra
    -0.69
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.69
    uster
    -0.68
    ãģ®éŃĶ
    -0.68
    cohol
    -0.67
    cedented
    -0.67
    etooth
    -0.66
    zzi
    -0.66
    POSITIVE LOGITS
    arily
    1.35
     biologist
    0.96
    ary
    0.95
    aeda
    0.93
    esis
    0.88
     biology
    0.86
    arium
    0.86
    etics
    0.85
    ozo
    0.79
    etically
    0.79
    Activations Density 0.037%

    No Known Activations