Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 9053
    Prev
    Next
    INDEX
    Explanations

    numeric ranges

    oai_token-act-pair · gpt-3.5-turbo

    numerical and statistical data related to measurements and quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Unch
    -0.61
    abase
    -0.60
    ipedia
    -0.59
    aband
    -0.54
     Sin
    -0.53
    arov
    -0.53
     Opening
    -0.53
     Toy
    -0.52
     Faster
    -0.52
    SourceFile
    -0.52
    POSITIVE LOGITS
     respectively
    1.10
     alike
    0.93
    depending
    0.81
     combo
    0.81
    whatever
    0.76
     architectures
    0.74
    SPONSORED
    0.68
     complexes
    0.67
     combination
    0.63
     economies
    0.63
    Activations Density 0.642%

    No Known Activations