© 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. 4-RES-JB
    11. 16766
    Prev
    Next
    INDEX
    Explanations

    quantitative values, especially focusing on numerical values being below a specific threshold

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical values indicating thresholds or limits that are less than a specified value

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

    No Comments

    Negative Logits
    RAW
    -0.82
    Choice
    -0.72
    Sense
    -0.70
    Language
    -0.68
    Creat
    -0.67
    Frames
    -0.67
    POSE
    -0.67
    MM
    -0.66
    Translation
    -0.65
    Array
    -0.65
    POSITIVE LOGITS
    ground
    0.82
    uckland
    0.76
    grade
    0.74
    cedented
    0.74
     lip
    0.74
    grading
    0.72
    querque
    0.72
     grade
    0.72
     artif
    0.72
    pping
    0.72
    Activations Density 0.021%

    No Known Activations