© 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. 13781
    Prev
    Next
    INDEX
    Explanations

    phrases related to a large quantity or proportion of something

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to quantities or counts of items

    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
     majesty
    -0.78
     deepest
    -0.72
     appre
    -0.66
    artisan
    -0.66
     slump
    -0.64
     inaction
    -0.61
    rador
    -0.60
     utmost
    -0.60
    heid
    -0.60
    ataka
    -0.60
    POSITIVE LOGITS
     of
    0.84
     (>
    0.76
    metry
    0.73
    enance
    0.71
    UID
    0.70
    dot
    0.66
    rw
    0.66
     (<
    0.66
    NUM
    0.66
    ONES
    0.65
    Activations Density 0.044%

    No Known Activations