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. 1-RES-JB
    6. 19764
    Prev
    Next
    INDEX
    Explanations

    dates written in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the sequence "01" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exha
    -0.93
    awaru
    -0.89
     hemor
    -0.85
     notor
    -0.79
     tradem
    -0.78
     hung
    -0.76
     unaff
    -0.74
     pressured
    -0.74
     volunte
    -0.74
     hypot
    -0.71
    POSITIVE LOGITS
    01
    1.28
    03
    1.14
    003
    1.12
    02
    1.10
    000000
    1.08
    009
    1.08
    0100
    1.07
    001
    1.07
    05
    1.07
    011
    1.06
    Activations Density 0.011%

    No Known Activations