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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 15732
    Prev
    Next
    INDEX
    Explanations

    instances where someone is physically sitting or standing on something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "sitting on."

    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
    anan
    -0.75
    rera
    -0.68
    essel
    -0.67
    YY
    -0.67
    rament
    -0.66
    ONSORED
    -0.66
    iam
    -0.65
    ists
    -0.65
    ynt
    -0.65
    cgi
    -0.64
    POSITIVE LOGITS
     behalf
    1.06
     top
    0.88
    shore
    0.85
     autop
    0.80
     rooft
    0.79
     fumes
    0.78
    eday
    0.77
     shore
    0.77
    etheless
    0.76
    erous
    0.75
    Activations Density 0.099%

    No Known Activations