© 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. 14471
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the source or basis of information or claims

    oai_token-act-pair · gpt-3.5-turbo
    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
     sucks
    -0.75
    alogue
    -0.72
    anooga
    -0.69
     thereof
    -0.64
    nob
    -0.63
     sugars
    -0.62
    lime
    -0.62
     Creator
    -0.61
    opath
    -0.60
    tool
    -0.59
    POSITIVE LOGITS
     several
    0.68
     numerous
    0.67
     locating
    0.67
    raltar
    0.65
     contacting
    0.62
     approximately
    0.61
    Reviewer
    0.61
     installing
    0.60
     Emblem
    0.60
     Naval
    0.59
    Activations Density 0.445%

    No Known Activations