© 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. 7-RES-JB
    11. 17192
    Prev
    Next
    INDEX
    Explanations

    dates and recurring events

    oai_token-act-pair · gpt-3.5-turbo

    references to occurrences or repetitions of events over time

    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
    ople
    -0.69
    hift
    -0.63
    orce
    -0.60
    ering
    -0.60
    ordes
    -0.60
    osterone
    -0.60
    otyp
    -0.59
    ysis
    -0.59
    ription
    -0.59
    dinand
    -0.59
    POSITIVE LOGITS
     consecutive
    0.85
     anniversary
    0.76
     Anniversary
    0.63
     consecut
    0.63
     apiece
    0.59
    isodes
    0.59
     approvals
    0.58
     hiatus
    0.58
     tying
    0.58
    âĶĢ
    0.58
    Activations Density 0.137%

    No Known Activations