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. 8-RES-JB
    6. 1592
    Prev
    Next
    INDEX
    Explanations

    hyphenated words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to collaboration or joint efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Slim
    -0.71
     Fitzgerald
    -0.69
     Faul
    -0.67
     Belle
    -0.67
     Thin
    -0.67
     Loll
    -0.66
     HELL
    -0.64
     Brah
    -0.62
     Kas
    -0.62
     Feast
    -0.62
    POSITIVE LOGITS
    founder
    1.29
    ordinate
    1.22
    operative
    1.22
    branded
    1.16
    authored
    1.14
    operation
    1.12
    existence
    1.10
    equal
    1.07
    signed
    1.06
    workers
    1.05
    Activations Density 0.040%

    No Known Activations