© 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. 1-RES-JB
    11. 20955
    Prev
    Next
    INDEX
    Explanations

    numerical values expressed as part of a code or sequence

    oai_token-act-pair · gpt-3.5-turbo

    sequences of non-standard characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entious
    -0.70
    mie
    -0.65
    ertation
    -0.60
    acea
    -0.60
    idity
    -0.60
    dullah
    -0.59
    ioned
    -0.59
    ODY
    -0.59
     RESP
    -0.58
    arah
    -0.58
    POSITIVE LOGITS
    ÃĹ
    1.10
    LAB
    0.79
    âĶĢâĶĢâĶĢâĶĢ
    0.77
     Expand
    0.76
    avier
    0.76
    _>
    0.75
    ±
    0.73
    Python
    0.73
    UX
    0.71
    —-
    0.68
    Activations Density 0.004%

    No Known Activations