© 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. 8-RES-JB
    11. 6923
    Prev
    Next
    INDEX
    Explanations

    distinguishing factors or unique qualities when comparing different things

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases highlighting distinctions between different subjects or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ossession
    -0.69
    earance
    -0.68
    ``
    -0.67
    aping
    -0.66
    later
    -0.64
    oke
    -0.63
    onding
    -0.63
    ree
    -0.63
    unity
    -0.62
     Nikki
    -0.61
    POSITIVE LOGITS
     kinds
    0.88
     eras
    0.86
     types
    0.85
     competitors
    0.81
     brands
    0.78
     countries
    0.78
     categories
    0.77
     nations
    0.77
     facets
    0.77
     places
    0.77
    Activations Density 0.127%

    No Known Activations