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. 8-RES-JB
    6. 14610
    Prev
    Next
    INDEX
    Explanations

    phrases related to "so far" or conditions up to a certain point

    oai_token-act-pair · gpt-3.5-turbo

    statements and claims about ongoing situations or developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     secondly
    -0.74
    cms
    -0.69
     THEN
    -0.65
     Secondly
    -0.64
    ":[
    -0.63
    borough
    -0.63
     afterwards
    -0.61
    amins
    -0.60
    icter
    -0.60
     Kills
    -0.59
    POSITIVE LOGITS
     only
    0.78
    Only
    0.68
    oké
    0.67
    only
    0.66
    onse
    0.62
    Recommend
    0.62
     untouched
    0.61
    operative
    0.61
     scant
    0.61
     unsuccessfully
    0.60
    Activations Density 0.296%

    No Known Activations