© 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. 19305
    Prev
    Next
    INDEX
    Explanations

    words ending with the letter 's'

    oai_token-act-pair · gpt-3.5-turbo

    the letter "s" or words containing the letter "s"

    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
    e
    -0.69
     congress
    -0.60
    i
    -0.60
    OSP
    -0.58
     chalk
    -0.57
    eh
    -0.56
    a
    -0.56
     fringe
    -0.56
     trench
    -0.56
     animosity
    -0.56
    POSITIVE LOGITS
    nyder
    1.12
    kaya
    1.09
    ourced
    1.09
    ourcing
    1.05
    ources
    1.05
    wered
    1.03
    leeve
    0.98
    atellite
    0.98
    olutions
    0.94
    ayers
    0.94
    Activations Density 0.114%

    No Known Activations