© 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. 3-RES-JB
    11. 1801
    Prev
    Next
    INDEX
    Explanations

    adjectives and verbs related to strengthening, sharpening, and improving physical objects or skills

    oai_token-act-pair · gpt-3.5-turbo

    iterations or variations of the word "tense" or related forms, as well as stress and reinforcement concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Celest
    -0.73
     Shelley
    -0.69
    rael
    -0.67
    ilet
    -0.66
    orks
    -0.66
     Photographer
    -0.66
     Legisl
    -0.64
     Wonderland
    -0.62
     UFOs
    -0.62
    ARDIS
    -0.61
    POSITIVE LOGITS
     tuning
    0.72
    baugh
    0.71
     grip
    0.71
    atism
    0.71
    eness
    0.69
     regimen
    0.68
     realism
    0.67
     grips
    0.66
     stick
    0.66
     footh
    0.65
    Activations Density 0.139%

    No Known Activations