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. 9-RES-JB
    6. 19093
    Prev
    Next
    INDEX
    Explanations

    section markers indicating where events are taking place or in numerical format

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to meetings and gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nare
    -0.70
     Corpus
    -0.65
     affected
    -0.64
     Rhode
    -0.63
     Sig
    -0.59
    ĨĴ
    -0.58
     Starr
    -0.58
     referen
    -0.58
     Rodgers
    -0.58
     Division
    -0.57
    POSITIVE LOGITS
    advertising
    1.12
    trade
    1.07
    shoot
    1.05
    beer
    1.04
    your
    1.02
    learn
    1.02
    everything
    1.01
    distance
    1.00
    home
    0.99
    leave
    0.97
    Activations Density 0.043%

    No Known Activations