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. 10-RES-JB
    6. 11798
    Prev
    Next
    INDEX
    Explanations

    words related to a strong or extreme degree of something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "st," which may indicate emphasis on state-related discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     friendly
    -0.70
     carriers
    -0.60
     Friendly
    -0.59
     limited
    -0.58
    EStream
    -0.58
     Republic
    -0.57
     Union
    -0.56
    ãģ®éŃĶ
    -0.56
     collaboration
    -0.56
     cooperation
    -0.55
    POSITIVE LOGITS
    ifling
    1.22
    inky
    1.21
    onew
    1.21
    upe
    1.20
    umbles
    1.19
    itched
    1.17
    alker
    1.14
    inging
    1.12
    oried
    1.12
    eeper
    1.12
    Activations Density 0.016%

    No Known Activations