© 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. 11-RES-JB
    11. 9859
    Prev
    Next
    INDEX
    Explanations

    prepositions and verb phrases related to a person's position or posture

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "lying on."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ividual
    -0.68
    essions
    -0.66
    inations
    -0.63
    ynt
    -0.61
    bats
    -0.60
    cade
    -0.57
    urations
    -0.57
    ults
    -0.57
    onom
    -0.57
    voice
    -0.57
    POSITIVE LOGITS
     top
    1.17
    top
    1.13
     rooft
    1.04
     shore
    0.94
     edge
    0.93
    shore
    0.91
     stret
    0.88
     pavement
    0.88
     sidewalks
    0.88
    tops
    0.87
    Activations Density 0.097%

    No Known Activations