© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 8003
    Prev
    Next
    INDEX
    Explanations

    phrases containing the letters "ch"

    oai_token-act-pair · gpt-3.5-turbo

    words related to food, specifically those that begin with "ch."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INGTON
    -0.68
    FORMATION
    -0.64
     Mechdragon
    -0.63
     Circus
    -0.62
    glass
    -0.61
     minded
    -0.60
    gaard
    -0.60
     Ajax
    -0.60
    PORT
    -0.60
     Soy
    -0.57
    POSITIVE LOGITS
    akra
    1.33
    icago
    1.25
    amps
    1.21
    isel
    1.21
    inese
    1.20
    ipping
    1.19
    ocobo
    1.18
    ivalry
    1.15
    asers
    1.15
    ieft
    1.15
    Activations Density 0.015%

    No Known Activations