© 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. 10-RES-JB
    11. 23304
    Prev
    Next
    INDEX
    Explanations

    names or terms that seem to be of personal or professional significance

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names

    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
     OWN
    -0.70
     swing
    -0.64
     pound
    -0.63
     litter
    -0.61
     ..."
    -0.60
     swarm
    -0.60
     Meet
    -0.60
     THREE
    -0.59
     agriculture
    -0.59
     house
    -0.59
    POSITIVE LOGITS
    owski
    1.17
    iewicz
    1.15
    baugh
    1.15
    inski
    1.14
    zinski
    1.13
    ansky
    1.12
    zynski
    1.10
    chuk
    1.10
    akis
    1.09
    kowski
    1.08
    Activations Density 0.279%

    No Known Activations