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. 0-RES-JB
    6. 8921
    Prev
    Next
    INDEX
    Explanations

    numbers related to measurements or quantities

    oai_token-act-pair · gpt-3.5-turbo

    the number '6' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tarn
    -0.65
    tain
    -0.61
     stand
    -0.61
     knowing
    -0.60
     pudding
    -0.60
     afore
    -0.59
     suff
    -0.58
     mimic
    -0.58
     stal
    -0.58
     secrecy
    -0.58
    POSITIVE LOGITS
    6
    3.14
    7
    2.44
    5
    2.43
    8
    2.37
    9
    2.23
    4
    2.20
    3
    1.99
    2
    1.82
    1
    1.66
    0
    1.62
    Activations Density 0.029%

    No Known Activations