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. 21304
    Prev
    Next
    INDEX
    Explanations

    common verbs used in instructions or explanations

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "there are."

    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
    matter
    -0.83
    iliation
    -0.71
    ename
    -0.71
    isition
    -0.70
    speak
    -0.70
    dom
    -0.69
    analysis
    -0.67
    ileaks
    -0.66
    aired
    -0.66
    Initialized
    -0.65
    POSITIVE LOGITS
     plenty
    1.20
     lots
    1.08
     exceptions
    1.07
     indications
    1.04
     many
    1.04
     countless
    1.03
     several
    1.02
     few
    1.01
     similarities
    0.97
     dozens
    0.97
    Activations Density 0.092%

    No Known Activations