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. 10-RES-JB
    6. 4243
    Prev
    Next
    INDEX
    Explanations

    specific years and terms often related to academic works

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twitch
    -0.77
    Streamer
    -0.74
    ãĥİ
    -0.71
    Lt
    -0.70
    âķ
    -0.68
     showers
    -0.66
     waited
    -0.64
    Players
    -0.64
     idols
    -0.64
     flashed
    -0.64
    POSITIVE LOGITS
     book
    1.30
     article
    1.30
     paper
    1.22
     dissertation
    1.21
     essay
    1.20
     seminal
    1.20
     study
    1.18
     bestselling
    1.14
     thesis
    1.11
     forthcoming
    1.11
    Activations Density 0.242%

    No Known Activations