© 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. 16314
    Prev
    Next
    INDEX
    Explanations

    words that refer to specific historical time periods, particularly 19th and 20th-century designations

    oai_token-act-pair · gpt-3.5-turbo

    references to historical time periods or centuries

    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
     Logged
    -0.69
     Misc
    -0.69
     yours
    -0.68
     Mush
    -0.66
     QC
    -0.64
     mine
    -0.63
     nu
    -0.61
     PID
    -0.60
     reflections
    -0.60
     reflection
    -0.59
    POSITIVE LOGITS
    century
    1.51
    party
    1.08
    hour
    0.97
    grade
    0.94
    generation
    0.93
    eyed
    0.92
    ann
    0.92
    rate
    0.90
    inning
    0.90
    ranked
    0.89
    Activations Density 0.067%

    No Known Activations