© 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. 6-RES-JB
    6. 7502
    Prev
    Next
    INDEX
    Explanations

    numerical values, likely associated with lists or rankings

    oai_token-act-pair · gpt-3.5-turbo

    instances of the numeral "1" in various contexts

    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
    awaru
    -0.87
     Lumpur
    -0.78
    apon
    -0.75
    ategory
    -0.72
    orative
    -0.69
    ato
    -0.68
    usalem
    -0.67
    azel
    -0.66
    ellow
    -0.65
    utic
    -0.64
    POSITIVE LOGITS
    st
    1.32
    Password
    1.12
    125
    1.10
    120
    1.05
    000000
    1.01
    128
    0.94
    0000000
    0.85
     sqor
    0.80
    123
    0.79
    GB
    0.77
    Activations Density 0.090%

    No Known Activations