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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 19689
    Prev
    Next
    INDEX
    Explanations

    phrases related to reaffirmation or confirmation of beliefs or commitments

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with reaffirmation and confirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WER
    -0.69
     Parenthood
    -0.69
     ACTION
    -0.67
     Keeper
    -0.67
    DragonMagazine
    -0.65
     Enterprise
    -0.65
     Meadow
    -0.64
     Immunity
    -0.64
    CHAT
    -0.63
     Origin
    -0.63
    POSITIVE LOGITS
    oning
    1.02
    itting
    1.00
    irmed
    0.99
    anging
    0.97
    ining
    0.93
    avored
    0.93
    irming
    0.91
    ixed
    0.89
    oding
    0.87
    ighed
    0.87
    Activations Density 0.037%

    No Known Activations