© 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. 4-RES-JB
    11. 22106
    Prev
    Next
    INDEX
    Explanations

    objects or concepts related to angles within text

    oai_token-act-pair · gpt-3.5-turbo

    references to angles in various contexts

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

    No Comments

    Negative Logits
    ãģ®éŃĶ
    -0.85
    weet
    -0.84
    isner
    -0.84
    raltar
    -0.82
    ingham
    -0.81
    ledged
    -0.81
    ULE
    -0.78
    urrent
    -0.78
    ularity
    -0.76
    essee
    -0.76
    POSITIVE LOGITS
     angle
    1.22
     brackets
    1.11
     angles
    1.09
     jerk
    0.89
     thereto
    0.82
     Angle
    0.81
     bends
    0.77
     flare
    0.74
    hog
    0.73
     tilt
    0.71
    Activations Density 0.019%

    No Known Activations