© 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 EvalsExportsinterp-engineNEWAPI 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. 5174
    Prev
    Next
    INDEX
    Explanations

    numbers mixed with letters that seem to represent specific data or codes

    oai_token-act-pair · gpt-3.5-turbo

    significant textual patterns or repetitions, particularly symbols and formatting elements

    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
    eworks
    -0.81
    ÄŁ
    -0.70
    conservancy
    -0.69
    oba
    -0.68
    atars
    -0.67
    eki
    -0.64
    quin
    -0.62
    eren
    -0.61
    iffe
    -0.61
    encers
    -0.61
    POSITIVE LOGITS
     TBA
    0.84
     Ibid
    0.83
     None
    0.79
     varies
    0.73
     Manual
    0.72
    None
    0.72
    */
    0.67
    Safety
    0.64
     none
    0.63
     Penalty
    0.62
    Activations Density 0.360%

    No Known Activations