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. 3-RES-JB
    6. 18740
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to physical grasp or control

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "grip" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DEF
    -0.70
    hex
    -0.66
    issy
    -0.66
    ffe
    -0.65
    ploy
    -0.64
    etheus
    -0.64
    ownt
    -0.64
    oha
    -0.63
    bsp
    -0.63
    DIV
    -0.62
    POSITIVE LOGITS
     grip
    1.22
     Grip
    1.12
     grips
    1.04
    hold
    0.87
     gripping
    0.79
    igator
    0.72
    eering
    0.72
    veland
    0.71
     gripped
    0.71
    vine
    0.71
    Activations Density 0.010%

    No Known Activations