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. 19403
    Prev
    Next
    INDEX
    Explanations

    numerical values corresponding to specific measurements, such as widths or heights

    oai_token-act-pair · gpt-3.5-turbo

    the specific numeric value "300" across various contexts

    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
    warts
    -0.81
    algia
    -0.80
    atories
    -0.74
    bid
    -0.74
    aken
    -0.72
    sole
    -0.72
    elli
    -0.71
    agan
    -0.71
    achi
    -0.71
    omin
    -0.70
    POSITIVE LOGITS
     msec
    0.76
    300
    0.76
    000
    0.75
    ONSORED
    0.75
     Leban
    0.72
     mosqu
    0.72
     millenn
    0.72
     resil
    0.70
     MHz
    0.70
     volts
    0.69
    Activations Density 0.015%

    No Known Activations