© 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. 7-RES-JB
    11. 18400
    Prev
    Next
    INDEX
    Explanations

    numbers in a specific format, likely related to a specific type of content or data

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number five in various contexts

    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
    swick
    -0.66
    icol
    -0.64
     Hort
    -0.63
    worldly
    -0.62
    sed
    -0.60
    perature
    -0.59
    ppo
    -0.59
    xual
    -0.58
     Herz
    -0.58
    opter
    -0.58
    POSITIVE LOGITS
    Thirty
    1.15
    âĺħ
    0.86
    th
    0.84
    010
    0.81
    0000
    0.81
     ILCS
    0.78
    678
    0.78
    teen
    0.77
    ths
    0.74
    teenth
    0.74
    Activations Density 0.114%

    No Known Activations