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. 6-RES-JB
    6. 19231
    Prev
    Next
    INDEX
    Explanations

    numerical values that are part of data or measurements

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or identifiers related to data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istically
    -0.82
    think
    -0.82
    holder
    -0.76
    estine
    -0.73
    ously
    -0.71
    blind
    -0.67
    athing
    -0.65
    pper
    -0.65
    eting
    -0.65
    anke
    -0.65
    POSITIVE LOGITS
     ILCS
    0.99
    é¾
    0.92
    mph
    0.86
     dB
    0.81
    374
    0.78
    503
    0.77
    20439
    0.77
    508
    0.76
    803
    0.73
    40
    0.73
    Activations Density 0.032%

    No Known Activations