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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 20797
    Prev
    Next
    INDEX
    Explanations

    time intervals or frequencies

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating frequency or repetition of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hess
    -0.68
    olas
    -0.64
     Journals
    -0.64
     Sakuya
    -0.62
     Jah
    -0.61
    ahime
    -0.60
    phabet
    -0.60
     Esports
    -0.59
     Carbuncle
    -0.58
     Grave
    -0.57
    POSITIVE LOGITS
    THING
    1.17
    where
    1.09
    single
    1.03
     year
    0.98
     month
    0.98
    day
    0.98
     imaginable
    0.98
     conceivable
    0.95
    WHERE
    0.93
     week
    0.92
    Activations Density 0.037%

    No Known Activations