© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7754
    Prev
    Next
    INDEX
    Explanations

    phrases indicating categorization or classification

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest a "sort of" or "kind of" expression

    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
    essors
    -0.89
    omers
    -0.85
    oons
    -0.84
    years
    -0.83
     Seconds
    -0.83
    ands
    -0.83
    anners
    -0.83
    ients
    -0.82
    inches
    -0.82
    aries
    -0.81
    POSITIVE LOGITS
     consolation
    0.90
     intermediary
    0.86
     existential
    0.84
     miracle
    0.84
     miraculous
    0.84
     ideological
    0.83
     afterlife
    0.82
     magic
    0.82
     mechanism
    0.82
     relationship
    0.80
    Activations Density 0.052%

    No Known Activations