© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23525
    Prev
    Next
    INDEX
    Explanations

    references to physical corners or locations in a space

    oai_token-act-pair · gpt-3.5-turbo

    the word "corner" and its variations or surrounding context that imply spatial or situational corners

    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
    emon
    -0.84
    inen
    -0.83
    egal
    -0.80
    ufact
    -0.79
    atoon
    -0.76
    emonic
    -0.75
    uthor
    -0.73
    ignt
    -0.73
    hur
    -0.73
    ploy
    -0.72
    POSITIVE LOGITS
    stones
    1.38
    bars
    0.96
     corner
    0.84
    stone
    0.83
    busters
    0.82
    bar
    0.81
    kick
    0.79
    ing
    0.79
     outfield
    0.78
     corners
    0.76
    Activations Density 0.032%

    No Known Activations