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. 11-RES-JB
    6. 18155
    Prev
    Next
    INDEX
    Explanations

    phrases related to physically grabbing or holding someone

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating physical actions or interactions involving grabbing or holding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.74
    iety
    -0.65
    agascar
    -0.64
    ³³
    -0.64
    thood
    -0.62
    speak
    -0.60
    abi
    -0.60
     oriented
    -0.60
     centered
    -0.58
    ERAL
    -0.58
    POSITIVE LOGITS
     horns
    1.03
     leash
    0.93
     collar
    0.84
     jaws
    0.82
     ankles
    0.82
     gates
    0.81
     belt
    0.81
     ropes
    0.81
     sword
    0.78
     sleeve
    0.78
    Activations Density 0.107%

    No Known Activations