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. 23045
    Prev
    Next
    INDEX
    Explanations

    verbs indicating continuity or persistence

    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
     wheels
    -0.60
     Stamford
    -0.59
     Houses
    -0.58
     pestic
    -0.57
    opian
    -0.56
    ouses
    -0.54
    BALL
    -0.53
     Bows
    -0.53
     Tycoon
    -0.52
     Hemp
    -0.52
    POSITIVE LOGITS
     thereof
    0.86
     thereafter
    0.83
     versa
    0.80
     hereafter
    0.79
    )*
    0.74
    existent
    0.73
    )
    0.73
    uala
    0.71
    )=
    0.69
     ?)
    0.67
    Activations Density 0.198%

    No Known Activations