© 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. 17353
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the act of placing or positioning something

    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
    ucci
    -0.72
    SB
    -0.71
    issance
    -0.69
    hess
    -0.64
    tub
    -0.61
    agher
    -0.60
    ery
    -0.59
    arb
    -0.59
    mpeg
    -0.58
    esome
    -0.58
    POSITIVE LOGITS
     bets
    1.14
     emphasis
    1.07
     blame
    1.01
    holders
    0.97
    holder
    0.92
     constraints
    0.79
     restrictions
    0.79
     undue
    0.78
     restraints
    0.78
     cursor
    0.78
    Activations Density 0.057%

    No Known Activations