© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7335
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Gam" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Gam" or related variations within a community context

    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
     chemotherapy
    -0.66
     dissolved
    -0.66
     politic
    -0.65
     consec
    -0.65
    weight
    -0.65
     compounded
    -0.64
     Wick
    -0.62
     bed
    -0.62
     510
    -0.61
    FU
    -0.60
    POSITIVE LOGITS
    ulative
    1.09
    bitious
    1.03
    blers
    1.02
    indust
    1.00
    azing
    0.99
    gam
    0.96
    ules
    0.94
    aji
    0.93
    raphic
    0.93
    eworks
    0.92
    Activations Density 0.007%

    No Known Activations