© 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. 520
    Prev
    Next
    INDEX
    Explanations

    the auxiliary verb 'does'

    oai_token-act-pair · gpt-4-turbo

    the word "does" in sentences

    oai_token-act-pair · gpt-3.5-turbo

    the word "does" in various contexts

    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
    haul
    -0.70
    rum
    -0.69
    ESA
    -0.68
     Vers
    -0.66
     Methods
    -0.66
     Canal
    -0.65
    Secondly
    -0.63
    case
    -0.63
    bilt
    -0.62
    bush
    -0.62
    POSITIVE LOGITS
    omething
    1.02
     not
    0.94
    ĸļ
    0.92
    ppel
    0.89
    omsday
    0.83
     NOT
    0.83
    ettings
    0.81
    omorphic
    0.80
    lez
    0.79
    oley
    0.79
    Activations Density 0.111%

    No Known Activations