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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 10-RES-JB
    6. 17276
    Prev
    Next
    INDEX
    Explanations

    unexpected or surprising outcomes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "turns out."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raltar
    -0.81
    aldi
    -0.69
    kel
    -0.68
    tymology
    -0.67
    ulkan
    -0.63
    prus
    -0.63
    asus
    -0.63
    TY
    -0.63
    ettlement
    -0.62
    berra
    -0.61
    POSITIVE LOGITS
     differently
    0.96
     alright
    0.91
     okay
    0.91
     to
    0.86
     ok
    0.83
     OK
    0.81
     horribly
    0.75
     badly
    0.74
     worse
    0.73
     beautifully
    0.72
    Activations Density 0.047%

    No Known Activations