© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 11040
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to physical grips or holds

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "grip" and related variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ô
    -0.68
    etheus
    -0.67
    enic
    -0.66
    GW
    -0.64
    itia
    -0.64
    hex
    -0.64
     Cemetery
    -0.63
     è£ıç
    -0.61
    DEF
    -0.61
     Referred
    -0.61
    POSITIVE LOGITS
    hold
    1.31
     grip
    1.07
     Grip
    0.99
     grips
    0.97
     tightly
    0.89
     grasp
    0.89
    lock
    0.88
     tightened
    0.86
    locks
    0.85
    fast
    0.84
    Activations Density 0.106%

    No Known Activations