Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 7676
    Prev
    Next
    INDEX
    Explanations

    dates and various technical terms or symbols

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RT
    -0.82
     Ri
    -0.78
     DAR
    -0.77
     Rw
    -0.76
    09
    -0.75
     RS
    -0.73
    RS
    -0.72
    iago
    -0.71
     ridge
    -0.71
     Ridley
    -0.70
    POSITIVE LOGITS
    70
    0.85
    oms
    0.82
    ana
    0.79
    ph
    0.77
    610
    0.76
    phant
    0.76
    690
    0.75
    metics
    0.75
    65
    0.75
     Plastic
    0.74
    Activations Density 0.445%

    No Known Activations