© 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. 7078
    Prev
    Next
    INDEX
    Explanations

    phrases indicating desire or preference

    oai_token-act-pair · gpt-3.5-turbo

    expressions questioning desires or preferences

    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
    bis
    -0.61
     Letter
    -0.59
    notations
    -0.59
     Oaks
    -0.56
    pc
    -0.56
    rams
    -0.55
    Runner
    -0.55
     Fargo
    -0.55
     variants
    -0.54
     requested
    -0.54
    POSITIVE LOGITS
    ?)
    1.18
    ?),
    1.16
    ?!
    1.14
    ?).
    1.10
    ?!"
    1.09
    !?"
    1.07
    ?"
    1.01
    ?
    1.00
    !?
    0.99
    ?'"
    0.92
    Activations Density 0.103%

    No Known Activations