© 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. 11-RES-JB
    11. 21340
    Prev
    Next
    INDEX
    Explanations

    mentions of job titles or positions, especially related to technology companies

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and specific brand or product names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Saint
    -0.84
     Phill
    -0.83
     Shelley
    -0.82
     Schl
    -0.82
     Box
    -0.80
     PS
    -0.80
     Kn
    -0.80
     Loch
    -0.80
     psi
    -0.79
     Larry
    -0.78
    POSITIVE LOGITS
    ad
    1.84
    ads
    1.73
    ada
    1.59
    AD
    1.58
    adic
    1.50
    adian
    1.45
    adas
    1.42
    aders
    1.39
    adi
    1.35
    ader
    1.34
    Activations Density 0.250%

    No Known Activations