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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 10791
    Prev
    Next
    INDEX
    Explanations

    numerical values related to quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to quantities and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awar
    -0.61
     thence
    -0.60
    uber
    -0.59
    NES
    -0.58
    verages
    -0.58
    bryce
    -0.57
    Ranked
    -0.57
    Ware
    -0.56
    ©¶æ
    -0.56
     Elys
    -0.56
    POSITIVE LOGITS
     000
    1.11
    %
    1.06
     million
    1.05
     thousand
    1.05
    %"
    1.01
     percent
    1.01
    00000
    0.93
    %.
    0.93
     years
    0.86
     varieties
    0.86
    Activations Density 0.131%

    No Known Activations