© 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. 2-RES-JB
    11. 9176
    Prev
    Next
    INDEX
    Explanations

    names or proper nouns starting with special characters

    oai_token-act-pair · gpt-3.5-turbo

    special characters and graphemes, particularly those related to certain names or terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lovecraft
    -0.82
     Blazers
    -0.74
    enged
    -0.72
     Dull
    -0.70
    etsk
    -0.70
    hess
    -0.68
     Pledge
    -0.67
    ifying
    -0.66
    urtle
    -0.66
    ifier
    -0.66
    POSITIVE LOGITS
     é
    1.12
    lé
    1.09
     Ãī
    1.06
    ÃįÃį
    1.06
    Ãī
    0.93
    rique
    0.88
    ternity
    0.86
    ¬
    0.83
    izoph
    0.80
    ité
    0.78
    Activations Density 0.009%

    No Known Activations