© 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. 0-RES-JB
    11. 22555
    Prev
    Next
    INDEX
    Explanations

    numerical values representing a collective total

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "combined" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thood
    -0.68
    lier
    -0.67
    terday
    -0.62
    jar
    -0.62
    gra
    -0.61
    eday
    -0.60
    grave
    -0.60
    dad
    -0.59
     tomorrow
    -0.59
    ze
    -0.59
    POSITIVE LOGITS
     combined
    3.88
     Combined
    2.10
     coupled
    1.97
     combine
    1.70
     combination
    1.63
     combining
    1.54
     blended
    1.50
     paired
    1.49
     merged
    1.47
    Comb
    1.39
    Activations Density 0.007%

    No Known Activations