© 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. 13315
    Prev
    Next
    INDEX
    Explanations

    mentions of specific time frames, such as years or decades

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods or events that started or occurred in recent history

    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
    united
    -0.64
    tons
    -0.63
    Done
    -0.62
     appl
    -0.58
     WITHOUT
    -0.58
    oeuv
    -0.58
    jac
    -0.56
    nit
    -0.56
     negro
    -0.56
    oreal
    -0.55
    POSITIVE LOGITS
     decade
    0.91
     decades
    0.84
     Watergate
    0.83
     late
    0.82
     1980
    0.82
     years
    0.81
     early
    0.80
     adolescence
    0.80
    ixties
    0.78
    eteenth
    0.78
    Activations Density 0.407%

    No Known Activations