© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 9893
    Prev
    Next
    INDEX
    Explanations

    texts with unusual characters, such as "Ċ", possibly indicating some unique formatting or encoding issue

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that mention statistics or data related to societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spitting
    -0.92
     yours
    -0.86
     ninja
    -0.84
     shelling
    -0.84
     grip
    -0.84
     swe
    -0.83
     swoop
    -0.83
     neighb
    -0.83
     craz
    -0.82
     rul
    -0.80
    POSITIVE LOGITS
    References
    1.68
    Methods
    1.65
    Figure
    1.62
    Recent
    1.62
    Introduction
    1.58
    FIG
    1.54
    Conclusion
    1.54
    Background
    1.53
    Discussion
    1.53
    CONCLUS
    1.53
    Activations Density 0.435%

    No Known Activations