© 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. 2-RES-JB
    11. 12462
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "devious" or words similar in sound to "deaf"

    oai_token-act-pair · gpt-3.5-turbo

    words related to deafness and deaf culture

    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
     warranted
    -0.67
     agg
    -0.65
     cue
    -0.64
    etheless
    -0.63
     shove
    -0.62
     incon
    -0.61
     clearance
    -0.61
     irregularities
    -0.61
    utra
    -0.59
    uesday
    -0.58
    POSITIVE LOGITS
    ciating
    1.20
    liction
    0.88
    enment
    0.86
    icio
    0.80
    iste
    0.77
    ibles
    0.76
    ctic
    0.76
    agram
    0.75
    agement
    0.75
    irs
    0.73
    Activations Density 0.157%

    No Known Activations