© 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. 4-RES-JB
    11. 14939
    Prev
    Next
    INDEX
    Explanations

    sensitive information

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of blocks in a technical context

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

    No Comments

    Negative Logits
    sonian
    -0.72
    ndra
    -0.61
     bour
    -0.61
    ITNESS
    -0.61
    fol
    -0.60
    hof
    -0.59
    verty
    -0.58
     Remastered
    -0.58
    ulner
    -0.58
     Saban
    -0.57
    POSITIVE LOGITS
     flats
    0.80
    webkit
    0.68
    Medium
    0.65
    vous
    0.63
    google
    0.60
    isite
    0.60
    alion
    0.60
    idity
    0.59
    monary
    0.59
    rolled
    0.58
    Activations Density 0.333%

    No Known Activations