© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-RES-JB
    11. 7435
    Prev
    Next
    INDEX
    Explanations

    mentions of specific days of the week

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of plural nouns and specific adjective forms related to animals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enhagen
    -0.69
    glers
    -0.68
    azing
    -0.68
     Cruiser
    -0.67
     Bei
    -0.62
    OSH
    -0.58
    boards
    -0.56
     Qing
    -0.56
    arity
    -0.55
     ASC
    -0.55
    POSITIVE LOGITS
    cript
    1.35
    cence
    1.28
    hift
    1.21
    pring
    1.21
    ilver
    1.18
    aurus
    1.18
    chool
    1.18
    cue
    1.18
    cu
    1.17
    creen
    1.15
    Activations Density 0.146%

    No Known Activations