© 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. 7-RES-JB
    11. 1783
    Prev
    Next
    INDEX
    Explanations

    timestamps in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numbers and timestamps

    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
    oked
    -0.75
    olitan
    -0.72
    ailable
    -0.71
    accompanied
    -0.67
    icum
    -0.66
    rongh
    -0.65
    etheless
    -0.65
    conservancy
    -0.64
    ribune
    -0.63
    cientious
    -0.62
    POSITIVE LOGITS
    âĶĢâĶĢâĶĢâĶĢ
    0.76
     Entered
    0.69
     ±
    0.67
     Wraith
    0.60
    ))))
    0.60
     Qi
    0.59
    Ùħ
    0.59
     Rowling
    0.58
    Jr
    0.58
     onwards
    0.58
    Activations Density 0.134%

    No Known Activations