© 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. 9-RES-JB
    11. 21185
    Prev
    Next
    INDEX
    Explanations

    Japanese characters and related phrases or names

    oai_token-act-pair · gpt-3.5-turbo

    symbols and characters from non-Latin scripts or languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anwhile
    -0.89
    ftime
    -0.78
     Beh
    -0.73
    seys
    -0.71
    espie
    -0.71
    sterdam
    -0.68
    theless
    -0.67
    brance
    -0.66
     agre
    -0.66
     dope
    -0.65
    POSITIVE LOGITS
    ¥
    1.80
    İ
    1.79
    Į
    1.75
    º
    1.74
    ¨
    1.69
    į
    1.69
    ı
    1.69
    ´
    1.67
    ±
    1.67
    »
    1.67
    Activations Density 0.021%

    No Known Activations