© 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. 8-RES-JB
    11. 20458
    Prev
    Next
    INDEX
    Explanations

    locations or directions indicated by the word "over"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "head over."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ivity
    -0.75
    itude
    -0.71
    iation
    -0.70
    iveness
    -0.65
    ï¸
    -0.64
     Beginning
    -0.61
    ias
    -0.60
    itudes
    -0.57
     Bullets
    -0.55
     perpet
    -0.55
    POSITIVE LOGITS
    tones
    0.74
    drive
    0.74
    WAR
    0.72
     stairs
    0.71
    roth
    0.70
    dule
    0.69
    hens
    0.68
     heels
    0.67
    shoot
    0.67
    population
    0.66
    Activations Density 0.068%

    No Known Activations