© 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. 3-RES-JB
    11. 4232
    Prev
    Next
    INDEX
    Explanations

    numerical characters and symbols in a specific pattern

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific non-standard character or symbol

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enfranch
    -0.83
    EStreamFrame
    -0.83
    ebus
    -0.80
    ãĥ£
    -0.79
    zona
    -0.76
    ItemImage
    -0.75
     reconc
    -0.72
     exha
    -0.69
    raints
    -0.69
    jri
    -0.68
    POSITIVE LOGITS
    ½
    1.06
    ×ķ
    0.92
    âĶĢâĶĢ
    0.91
    ת
    0.87
    е
    0.84
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.83
    ħ
    0.83
    и
    0.82
    а
    0.82
    Ñĥ
    0.81
    Activations Density 0.008%

    No Known Activations