© 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. 0-RES-JB
    11. 20261
    Prev
    Next
    INDEX
    Explanations

    angles or references to angles in a physical context

    oai_token-act-pair · gpt-3.5-turbo

    references to angles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SERV
    -0.71
     Particip
    -0.68
    uria
    -0.66
     Voting
    -0.66
    ren
    -0.65
    urs
    -0.65
    voc
    -0.63
    uel
    -0.63
    cknowled
    -0.62
    repl
    -0.62
    POSITIVE LOGITS
     angle
    3.86
     angles
    3.36
     Angle
    2.31
     angled
    1.63
    angle
    1.46
     vantage
    1.44
     tilt
    1.34
    angles
    1.21
     perspective
    1.20
     axis
    1.18
    Activations Density 0.020%

    No Known Activations