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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 19600
    Prev
    Next
    INDEX
    Explanations

    instances of the word "poke" or related words with varying degrees of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "poke" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingham
    -0.83
    hon
    -0.69
     Concord
    -0.67
    recy
    -0.66
    idal
    -0.66
    Decl
    -0.65
    effective
    -0.63
    demand
    -0.62
    national
    -0.61
    Quality
    -0.60
    POSITIVE LOGITS
     poking
    1.29
     poke
    1.21
     poked
    1.08
     disse
    0.83
    cheon
    0.80
    ature
    0.78
    duino
    0.77
     Poke
    0.77
    tesy
    0.73
     peek
    0.73
    Activations Density 0.012%

    No Known Activations