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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 19838
    Prev
    Next
    INDEX
    Explanations

    medical professionals or experts and their associated specialization areas

    oai_token-act-pair · gpt-3.5-turbo

    references to professional advice or consultation services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qqa
    -0.82
    ilib
    -0.81
    terday
    -0.77
    ãĥł
    -0.68
    "]=>
    -0.65
    BALL
    -0.65
     salute
    -0.63
     votes
    -0.63
    eki
    -0.62
    tons
    -0.62
    POSITIVE LOGITS
     reputable
    1.36
     specialist
    1.20
     therapist
    1.16
     knowledgeable
    1.09
     trusted
    1.08
     trustworthy
    1.08
     counselling
    1.05
     specialists
    1.05
     competent
    1.04
     counselor
    1.02
    Activations Density 0.599%

    No Known Activations