© 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. 9884
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific titles, terms, or brands mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to health and medical conditions

    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
     sped
    -0.59
     dashed
    -0.58
     conserv
    -0.57
    anwhile
    -0.56
     referen
    -0.54
    heastern
    -0.54
     fortified
    -0.54
     accelerated
    -0.52
     protected
    -0.52
     complementary
    -0.52
    POSITIVE LOGITS
     Syndrome
    0.89
    opia
    0.80
    Fest
    0.78
     Productions
    0.72
    Wiki
    0.72
    topia
    0.67
    ventures
    0.66
    Mania
    0.66
    Fit
    0.65
    Gate
    0.64
    Activations Density 0.778%

    No Known Activations