© 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. 7-RES-JB
    11. 2723
    Prev
    Next
    INDEX
    Explanations

    significant negative developments or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to comparisons of growth rates over time

    oai_token-act-pair · gpt-3.5-turbo
    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
     CPUs
    -0.58
     ("
    -0.55
    verse
    -0.53
    etc
    -0.52
    owered
    -0.51
     Allied
    -0.51
    bia
    -0.51
    ordering
    -0.51
    inducing
    -0.50
    osite
    -0.50
    POSITIVE LOGITS
    %"
    1.02
    [/
    0.99
    displayText
    0.89
    ,''
    0.87
    ?'
    0.85
    }"
    0.84
     âĢ
    0.84
    */(
    0.78
    ãĢı
    0.78
    ãĢ
    0.77
    Activations Density 0.745%

    No Known Activations