© 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. 17704
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific type of situation or issue

    oai_token-act-pair · gpt-3.5-turbo

    recurring references to types or categories of issues or problems

    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
     Bars
    -0.63
    alus
    -0.63
     Doors
    -0.62
    agnar
    -0.59
     Kod
    -0.57
     Balls
    -0.57
     Mellon
    -0.55
    weed
    -0.54
    unes
    -0.53
    rones
    -0.53
    POSITIVE LOGITS
     of
    1.08
    Of
    0.94
    of
    0.88
    hearted
    0.86
     OF
    0.84
     Of
    0.83
    lihood
    0.77
    liness
    0.75
    etting
    0.75
     thereof
    0.75
    Activations Density 0.038%

    No Known Activations