© 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. 16778
    Prev
    Next
    INDEX
    Explanations

    references to future time frames, specifically "weeks", "months", "days", and combinations of these terms

    oai_token-act-pair · gpt-3.5-turbo

    references to future time periods

    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
    nered
    -0.76
    ¬¼
    -0.69
     knack
    -0.65
     kissed
    -0.64
    edIn
    -0.64
    ocker
    -0.63
     DUI
    -0.61
    quartered
    -0.60
     wrong
    -0.60
     lately
    -0.60
    POSITIVE LOGITS
    .<
    0.80
    hops
    0.76
     onwards
    0.75
     Aviv
    0.75
     installments
    0.75
    olesc
    0.75
     Micha
    0.71
    ":"/
    0.70
    rica
    0.69
    ãĥĹ
    0.69
    Activations Density 0.086%

    No Known Activations