© 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. 7-RES-JB
    11. 12568
    Prev
    Next
    INDEX
    Explanations

    locations or names with the suffix "-ago"

    oai_token-act-pair · gpt-3.5-turbo

    references to time periods in the past

    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
    earchers
    -0.71
    soever
    -0.68
    ividual
    -0.67
     uniqueness
    -0.67
    Quantity
    -0.67
     confir
    -0.67
    Subject
    -0.66
    mble
    -0.66
    glass
    -0.66
    ifier
    -0.66
    POSITIVE LOGITS
    vernment
    1.37
    zzi
    1.37
    zzo
    1.06
    onga
    1.04
    zes
    1.04
    ÄŁ
    0.99
    zo
    0.97
    orthy
    0.97
    ppy
    0.96
    zeb
    0.95
    Activations Density 0.044%

    No Known Activations