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. 9-RES-JB
    6. 12838
    Prev
    Next
    INDEX
    Explanations

    phrases indicating important events or moments in time

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "when."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ertain
    -0.76
    whatever
    -0.70
    plus
    -0.67
    ggles
    -0.66
    vre
    -0.66
    bear
    -0.65
    augh
    -0.64
    agin
    -0.63
    ilus
    -0.63
    Grade
    -0.62
    POSITIVE LOGITS
    soever
    1.27
     they
    0.88
    upon
    0.84
     confronted
    0.77
     hackers
    0.75
     someone
    0.73
     hordes
    0.73
     suddenly
    0.72
     he
    0.70
     gunmen
    0.69
    Activations Density 0.106%

    No Known Activations