© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 5057
    Prev
    Next
    INDEX
    Explanations

    numerical values followed by a specific measurement or quantification

    oai_token-act-pair · gpt-3.5-turbo

    numbers, particularly those related to statistics and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    medi
    -0.68
    ãĥ¼ãĥ³
    -0.63
    folk
    -0.63
    Fram
    -0.62
    vati
    -0.61
    ettings
    -0.60
    plan
    -0.59
    reply
    -0.59
    venge
    -0.58
    que
    -0.58
    POSITIVE LOGITS
    %
    1.27
    %-
    1.20
     percent
    1.17
    %"
    1.13
    %.
    1.06
    mph
    1.01
    th
    1.01
    %:
    0.99
    %;
    0.99
    %,
    0.99
    Activations Density 0.160%

    No Known Activations