© 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. 11-RES-JB
    11. 10086
    Prev
    Next
    INDEX
    Explanations

    words related to online sources or content posting

    oai_token-act-pair · gpt-3.5-turbo

    special characters or formatting related to web links and paths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pora
    -0.75
     Ae
    -0.64
    inctions
    -0.61
    æĪ¦
    -0.61
    irie
    -0.61
    ratulations
    -0.60
    piration
    -0.59
    pire
    -0.58
    çķ
    -0.57
     Nab
    -0.55
    POSITIVE LOGITS
    t
    0.89
    icer
    0.76
    T
    0.72
    TL
    0.70
    TD
    0.67
    ts
    0.64
    ¹
    0.64
    ª
    0.63
    schild
    0.63
    ti
    0.62
    Activations Density 0.102%

    No Known Activations