© 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. 19798
    Prev
    Next
    INDEX
    Explanations

    words related to confirming or agreeing with a statement or belief

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating affirmation or endorsement

    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
    devices
    -0.72
    Ox
    -0.72
    hy
    -0.68
    OTOS
    -0.66
    sites
    -0.66
    bags
    -0.65
    ONES
    -0.65
    Spoiler
    -0.65
    hner
    -0.63
     Gorge
    -0.62
    POSITIVE LOGITS
     affirm
    1.37
    irmation
    1.31
     affirmation
    1.31
    irming
    1.26
    irmed
    1.26
    irm
    1.09
    irms
    1.03
    atively
    0.98
     reaff
    0.92
     acceptance
    0.84
    Activations Density 0.012%

    No Known Activations