© 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. 10-RES-JB
    11. 2903
    Prev
    Next
    INDEX
    Explanations

    phrases related to needing or searching for a specific person with certain qualities

    oai_token-act-pair · gpt-3.5-turbo

    references to the need for specific people or qualifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utenberg
    -0.67
    ovember
    -0.63
    inth
    -0.62
     culmin
    -0.60
     concludes
    -0.59
    Closure
    -0.56
     incorrectly
    -0.55
     snowball
    -0.55
     Revelations
    -0.54
    Operation
    -0.54
    POSITIVE LOGITS
     willing
    1.41
     whom
    1.17
     who
    1.14
     capable
    1.14
     suitable
    1.08
    who
    1.05
     trustworthy
    1.03
     whose
    0.94
     sympathetic
    0.92
     knowledgeable
    0.91
    Activations Density 0.364%

    No Known Activations