© 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. 693
    Prev
    Next
    INDEX
    Explanations

    proper names preceded by initials

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals, particularly those with the initial "R."

    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
     Connie
    -0.62
     vein
    -0.61
     resists
    -0.61
     Taiwanese
    -0.61
     regards
    -0.60
     Madame
    -0.59
     welcome
    -0.59
     pleas
    -0.59
     Romeo
    -0.58
     trapping
    -0.58
    POSITIVE LOGITS
    itchie
    1.52
    ansom
    1.42
    ector
    1.35
    abin
    1.33
    ourke
    1.29
    iggs
    1.23
    ugg
    1.23
    iddle
    1.22
    ommel
    1.21
    undle
    1.21
    Activations Density 0.034%

    No Known Activations