© 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. 11-RES-JB
    11. 2466
    Prev
    Next
    INDEX
    Explanations

    items being physically picked up or held

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to picking up or gathering physical objects

    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
    xual
    -1.02
    humans
    -0.76
    ysical
    -0.75
    yout
    -0.73
    ghai
    -0.73
    apesh
    -0.73
    htaking
    -0.73
    lees
    -0.72
    nels
    -0.72
    gae
    -0.71
    POSITIVE LOGITS
     clipboard
    1.09
     slack
    1.03
     towel
    1.00
     shovel
    0.96
     Pieces
    0.94
     reins
    0.93
     bags
    0.91
     suitcase
    0.91
     tray
    0.90
     pencil
    0.89
    Activations Density 0.144%

    No Known Activations