© 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. 14624
    Prev
    Next
    INDEX
    Explanations

    expressions related to quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    quantifiable comparisons and measurements

    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
    jen
    -0.68
    uesday
    -0.65
     Puzzle
    -0.60
    chool
    -0.60
     Athlet
    -0.56
    rame
    -0.56
     prone
    -0.56
     Chall
    -0.56
     Cipher
    -0.55
     doomed
    -0.55
    POSITIVE LOGITS
     equivalents
    0.87
     abundance
    0.81
    been
    0.79
    zero
    0.76
     hindsight
    0.75
     flair
    0.74
     capability
    0.73
     permission
    0.73
     advantages
    0.73
    undreds
    0.72
    Activations Density 0.506%

    No Known Activations