© 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. 7-RES-JB
    11. 286
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to disagreement or conflict

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dis" and its variations, indicating a focus on negative or problematic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hetti
    -0.72
    glers
    -0.71
     Kinnikuman
    -0.70
    DragonMagazine
    -0.67
     Juliet
    -0.66
     Osw
    -0.65
    OPLE
    -0.65
     Metatron
    -0.65
     Lans
    -0.63
     Scotia
    -0.63
    POSITIVE LOGITS
    cipl
    1.14
    ruption
    1.12
    enfranch
    1.11
    qus
    1.11
    rup
    1.10
    cerning
    1.09
    claimer
    1.09
    placed
    1.06
    comfort
    1.04
    plays
    1.04
    Activations Density 0.014%

    No Known Activations