Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 12608
    Prev
    Next
    INDEX
    Explanations

    words related to people or places, possibly focusing on specific individuals or locations

    oai_token-act-pair · gpt-3.5-turbo

    high-frequency occurrences of the substring "av"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Turing
    -0.77
    sofar
    -0.69
    utenant
    -0.68
     fog
    -0.67
     poppy
    -0.65
     tug
    -0.65
     unfor
    -0.65
     handy
    -0.65
     porous
    -0.65
    cold
    -0.64
    POSITIVE LOGITS
    av
    1.20
    irus
    1.11
    oided
    1.02
    ascular
    1.01
    atars
    1.00
    ille
    1.00
    arro
    1.00
    itus
    0.97
    atar
    0.97
    irtual
    0.96
    Activations Density 0.009%

    No Known Activations