© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 11585
    Prev
    Next
    INDEX
    Explanations

    phrases related to a large quantity or portion of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that frequently begin with "much of" followed by a noun or noun phrase

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chairs
    -0.75
     Cosponsors
    -0.75
    cards
    -0.73
    Enh
    -0.64
    bid
    -0.63
     pige
    -0.62
    pecially
    -0.61
    ants
    -0.61
    dayName
    -0.61
     Proxy
    -0.61
    POSITIVE LOGITS
    heastern
    0.75
    aution
    0.74
     Nort
    0.70
    olated
    0.69
     coastline
    0.67
     southeastern
    0.65
    amaru
    0.64
    éĸ
    0.64
     groundwork
    0.64
     misinformation
    0.63
    Activations Density 0.062%

    No Known Activations