© 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. 15727
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to places, organizations, or regulatory bodies

    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
     Pieces
    -0.69
    umblr
    -0.65
    watching
    -0.62
     Niet
    -0.61
    Redd
    -0.61
    getic
    -0.60
    unal
    -0.59
    tnc
    -0.58
     Hits
    -0.58
     Romero
    -0.58
    POSITIVE LOGITS
     offer
    1.28
     utilize
    1.23
     boast
    1.21
     rely
    1.21
     specialize
    1.20
     incorporate
    1.19
     employ
    1.18
     contain
    1.18
     require
    1.17
     advertise
    1.15
    Activations Density 0.286%

    No Known Activations