© 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. 9-RES-JB
    11. 9958
    Prev
    Next
    INDEX
    Explanations

    phrases related to alignment or agreement

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to alignment or coordination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilk
    -0.80
    loo
    -0.75
    HAEL
    -0.71
    oho
    -0.67
    sein
    -0.65
    perty
    -0.64
    bara
    -0.63
    ascus
    -0.63
    ek
    -0.60
    hell
    -0.60
    POSITIVE LOGITS
    ments
    1.36
    iances
    1.02
    arity
    0.96
    eering
    0.93
    ment
    0.91
    icut
    0.87
    pointers
    0.81
    mentation
    0.77
    ations
    0.76
     alignment
    0.75
    Activations Density 0.037%

    No Known Activations