Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 23637
    Prev
    Next
    INDEX
    Explanations

    words related to distribution systems and processes

    oai_token-act-pair · gpt-3.5-turbo

    references to distribution systems and processes

    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
    answered
    -0.75
     Joined
    -0.67
    aug
    -0.67
    ysc
    -0.66
    aughs
    -0.66
    bec
    -0.66
    nee
    -0.65
    elli
    -0.65
     undone
    -0.65
    pee
    -0.64
    POSITIVE LOGITS
     distribution
    3.86
     Distribution
    3.02
     distributions
    2.71
     distribute
    2.12
     Distribut
    2.10
     distributing
    2.09
     distributor
    1.92
     distribut
    1.86
     distributed
    1.83
     distributors
    1.77
    Activations Density 0.021%

    No Known Activations