© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3106
    Prev
    Next
    INDEX
    Explanations

    requests for feedback

    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
    orp
    -0.72
    istration
    -0.72
    uably
    -0.72
    arcity
    -0.70
    PHOTOS
    -0.69
    ila
    -0.68
    alias
    -0.67
    anova
    -0.66
    isoft
    -0.65
    igsaw
    -0.64
    POSITIVE LOGITS
     voices
    1.11
     hear
    0.89
     aloud
    0.86
     Voices
    0.85
     footsteps
    0.82
     louder
    0.81
    cliffe
    0.81
     heard
    0.80
     hearing
    0.80
     confessions
    0.80
    Activations Density 0.033%

    No Known Activations