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. 1-RES-JB
    6. 19962
    Prev
    Next
    INDEX
    Explanations

    specific terms represented by the letter 'X' followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to specific model names or designations in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getic
    -0.81
    assetsadobe
    -0.73
     respons
    -0.71
    ,,,,,,,,
    -0.70
     à¤
    -0.69
    inally
    -0.67
    è¦ļéĨĴ
    -0.66
    м
    -0.66
    kson
    -0.66
     Tot
    -0.64
    POSITIVE LOGITS
    avier
    1.08
    peria
    1.04
    III
    1.03
    X
    0.96
    xon
    0.95
    ML
    0.94
    cellence
    0.92
    BOX
    0.91
    XT
    0.91
    IX
    0.91
    Activations Density 0.015%

    No Known Activations