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. 9-RES-JB
    6. 6409
    Prev
    Next
    INDEX
    Explanations

    specific years in association with sports events or achievements

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.74
    nance
    -0.72
    ographers
    -0.68
    heit
    -0.68
    ourced
    -0.65
    sels
    -0.64
    .............
    -0.64
    strap
    -0.63
    âĢİ
    -0.63
    Leaks
    -0.62
    POSITIVE LOGITS
     midst
    1.27
     playoffs
    1.22
     semifinals
    1.07
     middle
    1.07
     postseason
    1.07
     meantime
    1.03
     finals
    0.99
     league
    0.99
     offseason
    0.98
     trenches
    0.98
    Activations Density 0.126%

    No Known Activations