© 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. 23535
    Prev
    Next
    INDEX
    Explanations

    verbs related to affirming or confirming statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to reaffirming commitments or positions

    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
     Lup
    -0.75
    AH
    -0.75
    OTA
    -0.74
     Created
    -0.71
     Galile
    -0.69
     Gray
    -0.68
     Golem
    -0.67
     Tul
    -0.67
     Hungry
    -0.67
    Leary
    -0.66
    POSITIVE LOGITS
    irmed
    1.43
    irming
    1.28
     reaff
    1.25
    irmation
    1.25
    irms
    1.13
    ront
    1.05
    licted
    0.96
    uates
    0.91
    bourg
    0.90
    irm
    0.88
    Activations Density 0.006%

    No Known Activations