© 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. 3-RES-JB
    11. 15247
    Prev
    Next
    INDEX
    Explanations

    instances where both entities are involved or affected

    oai_token-act-pair · gpt-3.5-turbo

    the word "both" indicating comparisons or dualities

    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
    renheit
    -0.79
    lé
    -0.78
    brace
    -0.77
    lo
    -0.73
    ugu
    -0.72
    lov
    -0.71
    krit
    -0.71
    ilit
    -0.71
    uez
    -0.71
    achment
    -0.71
    POSITIVE LOGITS
     sexes
    1.40
     genders
    1.19
     sides
    1.17
     halves
    1.11
     kinds
    0.80
     coasts
    0.80
     extremes
    0.79
     ends
    0.78
     parties
    0.78
    ocating
    0.76
    Activations Density 0.047%

    No Known Activations