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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 7808
    Prev
    Next
    INDEX
    Explanations

    references to successful and prominent entities and concepts within various industries

    oai_token-act-pair · gpt-3.5-turbo

    references to films, TV shows, and their creators

    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
    udos
    -0.62
    amia
    -0.62
    iversary
    -0.61
    iter
    -0.60
    oba
    -0.58
    ©¶æ
    -0.58
    aug
    -0.57
    owship
    -0.56
    天
    -0.56
    atorium
    -0.56
    POSITIVE LOGITS
     such
    2.15
     like
    1.94
    such
    1.79
     LIKE
    1.42
     including
    1.41
    like
    1.23
    Such
    1.16
     Like
    1.15
     ranging
    1.12
     Such
    1.09
    Activations Density 1.355%

    No Known Activations