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. 9-RES-JB
    6. 15057
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or places

    oai_token-act-pair · gpt-3.5-turbo

    references to "spot" or instances where something is highlighted or emphasized

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -0.82
    yss
    -0.65
    racuse
    -0.64
    velt
    -0.61
     pend
    -0.61
    jri
    -0.59
    ÄŁ
    -0.59
    wake
    -0.59
     Miko
    -0.58
     adolesc
    -0.58
    POSITIVE LOGITS
    lights
    1.65
    light
    1.13
    ter
    1.12
    lighting
    1.05
    ters
    1.03
    ty
    1.00
    ting
    0.97
    tery
    0.96
    pots
    0.95
    lot
    0.90
    Activations Density 0.042%

    No Known Activations