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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 10038
    Prev
    Next
    INDEX
    Explanations

    phrases related to the adjective "straight"

    oai_token-act-pair · gpt-3.5-turbo

    the word "straight" and its various usages in different contexts

    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
    endor
    -0.74
    andel
    -0.72
    rade
    -0.71
    Memory
    -0.67
    uria
    -0.67
    akens
    -0.66
    ITNESS
    -0.65
    aspers
    -0.64
    organ
    -0.63
    Effects
    -0.61
    POSITIVE LOGITS
     straight
    3.71
    straight
    3.04
     Straight
    2.61
     consecutive
    1.59
    Stra
    1.58
     stra
    1.30
     straightforward
    1.23
     heterosexual
    1.18
     directly
    1.02
     direct
    0.98
    Activations Density 0.007%

    No Known Activations