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

    Neuronpedia

    APICircuit 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. 6-RES-JB
    6. 18015
    Prev
    Next
    INDEX
    Explanations

    events or occasions that are to occur in a specific location or time

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "held" in reference to events or gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ately
    -0.71
    odor
    -0.68
    include
    -0.67
     deceive
    -0.63
     bandits
    -0.62
    clerosis
    -0.61
    naire
    -0.61
     Typh
    -0.59
    ————
    -0.59
    ocious
    -0.59
    POSITIVE LOGITS
     accountable
    0.97
     hostage
    0.94
     captive
    0.82
    erness
    0.80
    holding
    0.79
     Held
    0.77
     vigil
    0.77
    ãĥĺ
    0.76
    hold
    0.75
    DOWN
    0.75
    Activations Density 0.028%

    No Known Activations