© 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. 4-RES-JB
    11. 7331
    Prev
    Next
    INDEX
    Explanations

    phrases containing the term "af"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix 'af' as well as variations of the terms 'AU' and 'saf'

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

    No Comments

    Negative Logits
    Water
    -0.75
     disinfect
    -0.74
     Fargo
    -0.74
     Patriarch
    -0.70
    DOWN
    -0.69
     Mothers
    -0.67
    Accessory
    -0.67
    PASS
    -0.66
    >[
    -0.63
    Plex
    -0.63
    POSITIVE LOGITS
    icion
    1.38
    rican
    1.35
    rica
    1.16
    riad
    1.11
    avorite
    1.07
    riend
    1.00
    eatures
    0.98
    alon
    0.94
    ghan
    0.93
    ranch
    0.91
    Activations Density 0.007%

    No Known Activations