© 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. 20230
    Prev
    Next
    INDEX
    Explanations

    links to additional information for further reading

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "Read more."

    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
    Ö¼
    -0.61
     utilizing
    -0.61
    ©¶æ¥µ
    -0.60
     sucker
    -0.55
    xtap
    -0.54
     endeavor
    -0.52
    umenthal
    -0.51
    bably
    -0.51
     misunder
    -0.51
    issance
    -0.50
    POSITIVE LOGITS
     VIDEOS
    0.77
    >>
    0.70
     âĨĴ
    0.65
     »
    0.63
    ...]
    0.60
     âĢº
    0.60
     Juliet
    0.59
    âĢ¦]
    0.59
    biz
    0.57
    Why
    0.57
    Activations Density 0.016%

    No Known Activations