© 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. 4-RES-JB
    11. 10294
    Prev
    Next
    INDEX
    Explanations

    emoticons and symbols

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols, particularly a specific character that appears multiple times

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

    No Comments

    Negative Logits
     dorm
    -0.70
    phrine
    -0.70
     Franch
    -0.68
    enium
    -0.67
    uded
    -0.65
     distilled
    -0.65
     coales
    -0.64
     contracted
    -0.64
    ynthesis
    -0.63
     guided
    -0.62
    POSITIVE LOGITS
    Ģ
    1.35
    ðŁĺ
    1.23
    Ħ
    1.21
    ³
    1.18
    ¼
    1.14
    Ĥ
    1.13
    ī
    1.13
    ¢
    1.13
    ¹
    1.10
    ķ
    1.09
    Activations Density 0.007%

    No Known Activations