© 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. 10013
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers related to movies, TV seasons, and series

    oai_token-act-pair · gpt-3.5-turbo

    references to sequels, series, or installments in a franchise

    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
    ertodd
    -0.85
    roleum
    -0.84
    ratom
    -0.82
    Connector
    -0.79
    tics
    -0.76
    puters
    -0.71
    jri
    -0.70
    iques
    -0.70
    bows
    -0.70
    ppings
    -0.70
    POSITIVE LOGITS
     installment
    1.66
     edition
    1.38
     episode
    1.31
     chapter
    1.27
     installments
    1.24
     iteration
    1.23
     incarnation
    1.15
     season
    1.07
     volume
    1.03
     batch
    1.01
    Activations Density 0.162%

    No Known Activations