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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21505
    Prev
    Next
    INDEX
    Explanations

    words related to physical grasping or holding

    oai_token-act-pair · gpt-3.5-turbo

    references to physical grasp or control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    actionDate
    -0.78
    DEF
    -0.76
    etheus
    -0.74
    ownt
    -0.69
    abad
    -0.65
    bsp
    -0.64
    asty
    -0.62
    DoS
    -0.62
    hemat
    -0.62
    ploy
    -0.62
    POSITIVE LOGITS
     grip
    1.06
     Grip
    0.97
     grips
    0.95
    hold
    0.88
    es
    0.81
    oire
    0.81
    eer
    0.76
    esville
    0.73
     levers
    0.72
    raint
    0.71
    Activations Density 0.022%

    No Known Activations