© 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. 13284
    Prev
    Next
    INDEX
    Explanations

    expressions related to time durations

    oai_token-act-pair · gpt-3.5-turbo

    references to numbers, particularly relating to quantities and durations

    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
    akov
    -0.73
     himself
    -0.73
    rogens
    -0.69
     herself
    -0.68
    utes
    -0.68
     myself
    -0.66
    arov
    -0.66
    rary
    -0.65
    actly
    -0.64
    rett
    -0.64
    POSITIVE LOGITS
     foray
    1.25
     flagship
    0.99
     namesake
    0.95
     headquarters
    0.93
     holdings
    0.91
     woes
    0.84
     motto
    0.83
     own
    0.82
     nem
    0.82
     mascot
    0.80
    Activations Density 0.306%

    No Known Activations