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

    Neuronpedia

    Jacobian LensNEW
    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. 24003
    Prev
    Next
    INDEX
    Explanations

    the word "approach" to make sense of contexts and concepts in different scenarios

    oai_token-act-pair · gpt-3.5-turbo

    mentions of different methodologies or strategies

    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
    gin
    -0.73
    ãĥ©ãĥ³
    -0.71
    cakes
    -0.71
    arus
    -0.70
     Wak
    -0.69
    rake
    -0.67
    cake
    -0.65
    ensen
    -0.65
    reported
    -0.64
    watching
    -0.63
    POSITIVE LOGITS
     approach
    0.97
     Approach
    0.92
     toward
    0.79
    ologies
    0.79
    ahime
    0.78
     approaches
    0.75
    ivist
    0.74
     towards
    0.74
    rait
    0.73
    olitan
    0.72
    Activations Density 0.033%

    No Known Activations