© 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. 7-RES-JB
    11. 2050
    Prev
    Next
    INDEX
    Explanations

    estimates and numerical figures

    oai_token-act-pair · gpt-3.5-turbo

    statements involving numerical estimates or predictions

    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
    enment
    -0.67
     congrat
    -0.65
     reminder
    -0.65
     reminding
    -0.64
    Authent
    -0.63
    riter
    -0.61
    mbuds
    -0.60
     reminded
    -0.59
     Machina
    -0.59
    Message
    -0.59
    POSITIVE LOGITS
     TOTAL
    0.94
     total
    0.93
     estimated
    0.92
     approximately
    0.92
    total
    0.86
     Estimated
    0.85
     costs
    0.85
     revenues
    0.83
     average
    0.83
     expenditures
    0.82
    Activations Density 0.249%

    No Known Activations