© 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. 12160
    Prev
    Next
    INDEX
    Explanations

    instances where two entities are involved in a shared experience or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "both" indicating shared experiences or actions

    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
    -0.83
    ugu
    -0.78
    ilit
    -0.70
    vernment
    -0.70
    biz
    -0.69
    ça
    -0.68
    Trend
    -0.68
    krit
    -0.67
    justice
    -0.66
    lo
    -0.66
    POSITIVE LOGITS
     sexes
    1.37
     sides
    1.23
     halves
    1.17
     genders
    1.15
    ocating
    0.85
     sets
    0.85
     thirds
    0.80
     coasts
    0.79
     kinds
    0.79
     parties
    0.77
    Activations Density 0.047%

    No Known Activations