© 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. 9199
    Prev
    Next
    INDEX
    Explanations

    words related to disguises or masquerading

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word 'query' and its variations

    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
     Cosponsors
    -0.64
     Feed
    -0.62
     permitting
    -0.62
     citation
    -0.60
     STATS
    -0.60
     RSS
    -0.59
     RELEASE
    -0.59
    ENDED
    -0.59
     sudden
    -0.59
     feed
    -0.58
    POSITIVE LOGITS
    quer
    1.31
    querade
    1.09
    ading
    0.97
    ÃŃa
    0.90
    ior
    0.86
    ay
    0.85
    aders
    0.83
    oise
    0.83
    ito
    0.82
    isons
    0.82
    Activations Density 0.009%

    No Known Activations