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. 6-RES-JB
    6. 3500
    Prev
    Next
    INDEX
    Explanations

    mentions of third-party entities or dependencies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of third-party entities and their interactions or dependencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DAY
    -0.87
     envy
    -0.77
    DEN
    -0.74
     Month
    -0.73
     Width
    -0.72
    2020
    -0.72
     2030
    -0.70
    SEE
    -0.70
    Quantity
    -0.69
    Hour
    -0.69
    POSITIVE LOGITS
     vendors
    0.90
     validation
    0.82
     filings
    0.78
     accommodation
    0.77
     interven
    0.75
     sellers
    0.75
     sensing
    0.74
     submissions
    0.73
     interference
    0.73
     quir
    0.72
    Activations Density 0.040%

    No Known Activations