Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 19265
    Prev
    Next
    INDEX
    Explanations

    sequences of words that indicate a series or sequence of events or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating repeated patterns or sequences of events

    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
    esse
    -0.62
    selves
    -0.60
    amina
    -0.59
    argon
    -0.58
    inez
    -0.57
    glers
    -0.56
    iov
    -0.55
    zan
    -0.55
    omo
    -0.54
    bones
    -0.53
    POSITIVE LOGITS
     of
    1.08
    Of
    0.79
    meal
    0.75
     Of
    0.74
     thereof
    0.74
     OF
    0.73
     finale
    0.66
    icle
    0.65
    icles
    0.65
    of
    0.63
    Activations Density 0.048%

    No Known Activations