© 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. 14479
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparisons or emphasizing intensity

    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
    john
    -0.57
    watching
    -0.55
     lookup
    -0.55
    enhagen
    -0.55
    ãĥ¯ãĥ³
    -0.54
    REC
    -0.53
     Halls
    -0.53
     charcoal
    -0.53
    MORE
    -0.52
     Burr
    -0.52
    POSITIVE LOGITS
    apy
    1.10
    oner
    0.99
    othe
    0.99
    othes
    0.98
    bered
    0.98
    oths
    0.90
    zin
    0.78
    pport
    0.77
    aps
    0.77
    CTV
    0.75
    Activations Density 0.028%

    No Known Activations