© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 3102
    Prev
    Next
    INDEX
    Explanations

    phrases related to categorization or classification

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate classifications or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pat
    -0.69
    nut
    -0.69
     Merchants
    -0.69
     Citiz
    -0.67
     Sidd
    -0.67
    chal
    -0.66
     Strateg
    -0.62
     Bosh
    -0.61
     Hemp
    -0.61
    atto
    -0.61
    POSITIVE LOGITS
    interstitial
    0.77
    generation
    0.71
    ulhu
    0.63
    ãĢĤ
    0.62
     characterize
    0.62
     everywhere
    0.61
    agate
    0.60
    chool
    0.60
     owing
    0.59
     converge
    0.58
    Activations Density 0.072%

    No Known Activations