© 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. 24518
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific entities or unique identifiers

    oai_token-act-pair · gpt-3.5-turbo

    noun phrases that introduce categories or classifications

    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
    oops
    -0.65
    undy
    -0.64
    omever
    -0.64
    aways
    -0.63
    wings
    -0.62
    angs
    -0.62
    riots
    -0.62
    ['
    -0.59
    enges
    -0.58
    >"
    -0.57
    POSITIVE LOGITS
     slang
    0.95
     acronym
    0.88
     abbre
    0.86
     pseudonym
    0.84
    pmwiki
    0.83
     adjective
    0.82
     noun
    0.79
     genus
    0.79
     genre
    0.78
     fallacy
    0.76
    Activations Density 0.312%

    No Known Activations