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. 3801
    Prev
    Next
    INDEX
    Explanations

    phrases relating to requests or instructions

    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
     divor
    -0.58
    iolet
    -0.57
    apor
    -0.56
     satur
    -0.56
     segreg
    -0.55
    flying
    -0.54
     blat
    -0.54
    redo
    -0.54
     quadru
    -0.53
     appropri
    -0.53
    POSITIVE LOGITS
     of
    0.86
     thereof
    0.74
    OF
    0.74
    aeper
    0.72
     Of
    0.72
     OF
    0.71
    oft
    0.68
     whims
    0.67
    forts
    0.65
    liest
    0.65
    Activations Density 0.207%

    No Known Activations