© 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. 24054
    Prev
    Next
    INDEX
    Explanations

    the phrase "take a look" in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest examining or reviewing something closely

    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
    iHUD
    -0.78
    theless
    -0.67
     Entity
    -0.63
    RIC
    -0.61
     overrun
    -0.56
    cffff
    -0.54
    ufact
    -0.53
    Uncommon
    -0.53
    ivari
    -0.51
     principal
    -0.51
    POSITIVE LOGITS
     at
    0.89
     below
    0.75
     inside
    0.74
    ahead
    0.73
    oscope
    0.71
     into
    0.70
    behind
    0.69
    finder
    0.68
    nings
    0.67
    at
    0.67
    Activations Density 0.025%

    No Known Activations