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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 10656
    Prev
    Next
    INDEX
    Explanations

    parts of code surrounded by specific characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of backticks or grave accents (`` ` ``)

    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
    phrine
    -0.76
     mills
    -0.74
     Mamm
    -0.67
     condem
    -0.64
     delinqu
    -0.64
     Jenner
    -0.64
     Glou
    -0.63
     therap
    -0.62
     dividing
    -0.62
     elim
    -0.61
    POSITIVE LOGITS
    ansas
    0.87
    taboola
    0.86
    bah
    0.81
    seq
    0.81
    daq
    0.80
    lein
    0.78
    rosis
    0.77
    pler
    0.76
    Vi
    0.75
    ns
    0.74
    Activations Density 0.017%

    No Known Activations