© 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 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. 0-RES-JB
    11. 12535
    Prev
    Next
    INDEX
    Explanations

    keywords or phrases related to specific criteria

    oai_token-act-pair · gpt-3.5-turbo

    terms related to standards or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    co
    -0.70
    rir
    -0.69
    hi
    -0.68
    aii
    -0.64
    oil
    -0.64
    shi
    -0.63
     spilled
    -0.58
    hen
    -0.58
    ront
    -0.57
     Appears
    -0.57
    POSITIVE LOGITS
     criteria
    3.57
     criterion
    2.59
     guidelines
    1.61
     thresholds
    1.57
     requirements
    1.53
     qualifications
    1.49
     checklist
    1.45
     categories
    1.42
     parameters
    1.39
     definitions
    1.36
    Activations Density 0.016%

    No Known Activations