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. 0-RES-JB
    6. 7199
    Prev
    Next
    INDEX
    Explanations

    mentions of services

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pearl
    -0.69
     convincing
    -0.69
    é¾
    -0.68
    chance
    -0.67
    pin
    -0.66
    ãĥİ
    -0.65
    gam
    -0.65
     clen
    -0.65
     ult
    -0.64
     atom
    -0.63
    POSITIVE LOGITS
     Services
    3.62
    Services
    2.73
     SERVICES
    2.47
     services
    2.36
    services
    2.28
     Service
    2.23
    Service
    1.82
     SERVICE
    1.81
     service
    1.59
    service
    1.55
    Activations Density 0.014%

    No Known Activations