© 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. 9-RES-JB
    11. 21183
    Prev
    Next
    INDEX
    Explanations

    locations or positions described in relation to an entity

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "next"

    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
    kay
    -0.80
    ische
    -0.69
    adic
    -0.63
    lore
    -0.62
    rosso
    -0.62
    anners
    -0.62
    rament
    -0.61
    adel
    -0.60
    ampions
    -0.59
    boys
    -0.59
    POSITIVE LOGITS
     door
    1.17
    door
    0.82
     Door
    0.81
     compr
    0.78
     neighbour
    0.73
     thereto
    0.72
     to
    0.71
     baseman
    0.69
     stairs
    0.67
     week
    0.66
    Activations Density 0.031%

    No Known Activations