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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 17690
    Prev
    Next
    INDEX
    Explanations

    instances where the document talks about analyzing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "analyze" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hold
    -0.85
    guard
    -0.83
    vic
    -0.80
    Torrent
    -0.73
    guards
    -0.73
    jet
    -0.72
    \\\\
    -0.71
     struck
    -0.70
    ruck
    -0.70
    binding
    -0.69
    POSITIVE LOGITS
     feasibility
    0.80
    ively
    0.80
    hap
    0.77
    opian
    0.74
     how
    0.69
     trends
    0.69
     tapes
    0.68
     favorably
    0.67
     specimens
    0.67
     anomalies
    0.66
    Activations Density 0.114%

    No Known Activations