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. 6397
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases contrasting different aspects or options

    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
    hire
    -0.67
    ª
    -0.65
    clud
    -0.61
    thouse
    -0.60
    endor
    -0.59
    aii
    -0.58
    vest
    -0.57
    okia
    -0.56
    orc
    -0.55
    arag
    -0.55
    POSITIVE LOGITS
    depending
    1.76
     Either
    1.47
     respectively
    1.41
     whichever
    1.38
     depending
    1.38
     Both
    1.26
    Either
    1.20
    Both
    1.14
    ichever
    1.08
     Whatever
    1.07
    Activations Density 0.902%

    No Known Activations