© 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. 7-RES-JB
    11. 20842
    Prev
    Next
    INDEX
    Explanations

    specific words that refer to actions or objects, particularly nouns

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases suggesting dependence or consequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AMA
    -0.54
     Medals
    -0.54
     contrad
    -0.54
     Caucus
    -0.52
     rhet
    -0.52
     Haas
    -0.52
     Hung
    -0.51
     disav
    -0.51
     ethn
    -0.50
    —
    -0.50
    POSITIVE LOGITS
    pires
    0.82
     accompanies
    0.79
    caster
    0.68
    itiveness
    0.67
    older
    0.67
    ivalry
    0.64
    pired
    0.64
    wegian
    0.63
    Fast
    0.63
    OULD
    0.62
    Activations Density 0.942%

    No Known Activations