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. 20597
    Prev
    Next
    INDEX
    Explanations

    words related to data security and information technology

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to data security and management

    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
    heit
    -0.88
    ahime
    -0.66
    builders
    -0.64
    civil
    -0.64
    bol
    -0.63
    majority
    -0.62
    inventoryQuantity
    -0.61
    DEV
    -0.61
     tracts
    -0.61
     Rite
    -0.59
    POSITIVE LOGITS
    nsics
    0.73
     format
    0.70
     formats
    0.70
     Format
    0.69
     encoding
    0.66
    çīĪ
    0.65
    orer
    0.62
    DragonMagazine
    0.62
    ror
    0.62
    ophon
    0.62
    Activations Density 0.533%

    No Known Activations