© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 11862
    Prev
    Next
    INDEX
    Explanations

    words related to physical objects or entities

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of food or culinary items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BIL
    -0.69
    ALLY
    -0.65
    KNOWN
    -0.64
     Niet
    -0.60
     VID
    -0.58
    brates
    -0.55
    AUT
    -0.54
     Galile
    -0.53
    æ©Ł
    -0.53
    Sav
    -0.53
    POSITIVE LOGITS
    hift
    1.43
    pace
    1.37
    cale
    1.34
    ucker
    1.34
    hip
    1.25
    mith
    1.23
    uits
    1.22
    creen
    1.20
    ilver
    1.18
    pring
    1.16
    Activations Density 0.190%

    No Known Activations