© 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. 0-RES-JB
    11. 8401
    Prev
    Next
    INDEX
    Explanations

    words related to dodgy or questionable actions or situations

    oai_token-act-pair · gpt-3.5-turbo

    words related to energy or vitality

    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
     strike
    -0.67
     Concord
    -0.64
     Fact
    -0.61
     value
    -0.59
    successfully
    -0.57
     Codex
    -0.57
     Viol
    -0.57
     Lever
    -0.57
     msec
    -0.56
     quotations
    -0.55
    POSITIVE LOGITS
    gy
    4.62
    GY
    2.11
    gie
    1.69
    Gy
    1.67
    gyn
    1.60
    ging
    1.51
    ged
    1.50
    gery
    1.43
    gin
    1.41
    ger
    1.40
    Activations Density 0.018%

    No Known Activations