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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 1050
    Prev
    Next
    INDEX
    Explanations

    instances where people encounter or bump into each other

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "run into."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atts
    -0.74
    arming
    -0.71
    iev
    -0.70
    end
    -0.69
    lege
    -0.67
    caster
    -0.67
    hop
    -0.66
    cham
    -0.66
    lime
    -0.66
    edition
    -0.65
    POSITIVE LOGITS
    ãĥķ
    0.77
    âĸijâĸij
    0.71
    -+-+
    0.69
    ODE
    0.66
    ãĤ´ãĥ³
    0.65
    ãĤ¨ãĥ«
    0.65
     attractions
    0.62
    ãĥīãĥ©ãĤ´ãĥ³
    0.62
    âĸĴ
    0.62
    OVA
    0.61
    Activations Density 0.027%

    No Known Activations