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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2569
    Prev
    Next
    INDEX
    Explanations

    instances of people walking in different scenarios

    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
     contraction
    -0.62
    ãĥķãĤ©
    -0.61
    rish
    -0.59
     wors
    -0.59
    Percent
    -0.58
     Remastered
    -0.58
    ãĥĩãĤ£
    -0.58
    è¦ļéĨĴ
    -0.57
    vell
    -0.57
    amins
    -0.56
    POSITIVE LOGITS
     onto
    1.32
     into
    1.29
     INTO
    1.17
     ashore
    1.01
    into
    0.99
     downstairs
    0.96
     past
    0.96
     away
    0.95
     onstage
    0.94
     upstairs
    0.89
    Activations Density 0.174%

    No Known Activations