© 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. 1-RES-JB
    11. 3861
    Prev
    Next
    INDEX
    Explanations

    words related to disagreement or conflict

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "diss" and its variations related to disassociation or disconnection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gat
    -0.79
     Ducks
    -0.71
    FORE
    -0.67
     Tell
    -0.67
     Goff
    -0.67
     Archdemon
    -0.66
     Kinnikuman
    -0.64
     Wales
    -0.63
     Times
    -0.63
    DAY
    -0.63
    POSITIVE LOGITS
    ociation
    1.31
    ipation
    1.15
     diss
    1.12
    oci
    1.07
    ension
    1.05
    ociated
    1.03
    imilar
    1.02
    ertation
    1.01
    ociate
    0.99
    ident
    0.99
    Activations Density 0.003%

    No Known Activations