© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 897
    Prev
    Next
    INDEX
    Explanations

    terms referring to biological samples or remains used for scientific study

    oai_token-act-pair · gpt-4-turbo

    terms related to biological specimens, specifically fossils

    oai_token-act-pair · gpt-3.5-turbo

    terms related to biological specimens and fossils

    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
    runner
    -0.72
    light
    -0.72
    burning
    -0.72
    linear
    -0.67
    orney
    -0.67
    outer
    -0.65
    Knight
    -0.65
    nut
    -0.65
    tan
    -0.64
    road
    -0.64
    POSITIVE LOGITS
     specimens
    1.57
     specimen
    1.27
    ĸļ
    1.04
    imens
    0.92
    ysis
    0.88
     Collection
    0.86
    arium
    0.85
     fossils
    0.83
     collectors
    0.80
     Photographer
    0.79
    Activations Density 0.006%

    No Known Activations