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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8943
    Prev
    Next
    INDEX
    Explanations

    measurements of distances in kilometers and miles

    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
    (&
    -0.76
    (
    -0.72
    :(
    -0.70
    Ͻ
    -0.66
    ness
    -0.66
    ([
    -0.64
    CLOSE
    -0.63
    (_
    -0.62
    eez
    -0.60
    :#
    -0.60
    POSITIVE LOGITS
    ridges
    0.64
    ãĥİ
    0.63
     apiece
    0.63
    utenberg
    0.54
     pione
    0.54
    ategory
    0.53
    Gy
    0.52
     magnification
    0.52
     respectively
    0.52
    agall
    0.52
    Activations Density 0.075%

    No Known Activations