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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 21233
    Prev
    Next
    INDEX
    Explanations

    phrases related to minimalism or simplicity, often including the word "bare."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bare" and phrases related to minimal requirements or essentials

    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
    abulary
    -0.82
     pestic
    -0.73
    arios
    -0.71
    isson
    -0.70
    utra
    -0.69
    obal
    -0.69
    uese
    -0.68
    CVE
    -0.68
    uyomi
    -0.67
    oldown
    -0.66
    POSITIVE LOGITS
    footed
    1.29
    bones
    1.24
    foot
    1.20
    faced
    1.14
    handed
    1.10
    feet
    1.07
    clad
    0.99
    chest
    0.98
    falls
    0.92
    lings
    0.90
    Activations Density 0.021%

    No Known Activations