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. 8-RES-JB
    6. 20693
    Prev
    Next
    INDEX
    Explanations

    phrases involving actions or scenarios that can be performed without a specific requirement or condition

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aire
    -0.70
    oret
    -0.61
    estern
    -0.61
    thouse
    -0.61
    geist
    -0.61
    ère
    -0.60
     Vald
    -0.59
    undrum
    -0.58
     Kinnikuman
    -0.58
    sis
    -0.58
    POSITIVE LOGITS
     necessarily
    0.87
     slightest
    0.73
     explicitly
    0.72
     oneself
    0.72
     whatsoever
    0.71
     consciously
    0.67
    obin
    0.67
     anymore
    0.63
    azz
    0.63
     anything
    0.63
    Activations Density 0.134%

    No Known Activations