© 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. 4-RES-JB
    11. 5091
    Prev
    Next
    INDEX
    Explanations

    years or time periods expressed as 'mid-[number]'

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "mid" associated with various decades

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

    No Comments

    Negative Logits
    edIn
    -0.79
    Magikarp
    -0.74
     Immunity
    -0.67
     Bearing
    -0.66
    itsch
    -0.63
     Galileo
    -0.63
     Benef
    -0.62
     Comet
    -0.62
    Reviewed
    -0.62
     Redemption
    -0.62
    POSITIVE LOGITS
    -'
    0.96
    iors
    0.92
    cellaneous
    0.90
    ummer
    0.89
    terms
    0.88
    season
    0.85
    century
    0.85
    mid
    0.83
    cture
    0.83
     mids
    0.82
    Activations Density 0.011%

    No Known Activations