© 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
    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. 18821
    Prev
    Next
    INDEX
    Explanations

    German words within sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to specific teams or players in sports contexts

    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
     curry
    -0.76
     Rivera
    -0.73
     Manila
    -0.71
     Cherokee
    -0.67
     Venezuelan
    -0.67
     Maduro
    -0.66
     Duterte
    -0.65
     Caesar
    -0.65
     Lima
    -0.65
     Cousins
    -0.64
    POSITIVE LOGITS
    ÃŁ
    1.18
    utsche
    1.17
    hr
    1.16
    cht
    1.12
    utsch
    1.11
    ichen
    1.09
    inen
    1.09
    isen
    1.09
    icht
    1.09
    uder
    1.08
    Activations Density 0.084%

    No Known Activations