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. 2191
    Prev
    Next
    INDEX
    Explanations

    references to quantities or measurements

    oai_token-act-pair · gpt-3.5-turbo
    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
     plagiar
    -0.83
     treason
    -0.80
     traitor
    -0.75
     congrat
    -0.75
     adultery
    -0.73
     deceit
    -0.73
     Libertarian
    -0.73
     scorn
    -0.72
     Attribution
    -0.70
     epigen
    -0.70
    POSITIVE LOGITS
     capacity
    1.38
     throughput
    1.21
    capacity
    1.19
     Capacity
    1.14
     accommodate
    1.14
     quota
    1.12
     manpower
    1.12
     occupancy
    1.11
     overcrowd
    1.07
     accommod
    1.07
    Activations Density 0.832%

    No Known Activations