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. 11-RES-JB
    6. 19768
    Prev
    Next
    INDEX
    Explanations

    text related to decisions and opinions

    oai_token-act-pair · gpt-3.5-turbo

    the presence of a specific symbol or character in the text

    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
     snail
    -0.82
     mainland
    -0.69
     Isle
    -0.68
     ric
    -0.68
     Mous
    -0.64
     antip
    -0.64
     DES
    -0.63
     DEM
    -0.62
     MET
    -0.62
     sacrific
    -0.61
    POSITIVE LOGITS
    Ŀ
    1.73
    ¡
    1.31
    ¦
    1.23
    °
    1.19
    ľ
    1.16
    ©
    1.15
    «
    1.13
    Ķ
    1.12
    ĸ
    1.10
    ¤
    1.08
    Activations Density 0.289%

    No Known Activations