© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 9841
    Prev
    Next
    INDEX
    Explanations

    sentences indicating something specific has been found or determined

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "be" in various forms and contexts

    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
    anwhile
    -0.86
    rones
    -0.76
    fortunately
    -0.68
    terday
    -0.66
    rouse
    -0.66
    inav
    -0.65
    enaries
    -0.65
    ãĥ¼ãĥ«
    -0.64
     Globe
    -0.63
    culosis
    -0.63
    POSITIVE LOGITS
     able
    0.88
    leeve
    0.82
     quite
    0.71
     influenced
    0.71
    fit
    0.70
     healthier
    0.68
    heading
    0.68
     nearing
    0.67
     unstoppable
    0.67
     synonymous
    0.67
    Activations Density 0.142%

    No Known Activations