© 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. 4-RES-JB
    11. 17231
    Prev
    Next
    INDEX
    Explanations

    the word "can't" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "can't" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CVE
    -0.94
    artifacts
    -0.71
     behavi
    -0.68
     Gleaming
    -0.67
     SetTextColor
    -0.64
    çĦ
    -0.64
     tremend
    -0.63
     rounding
    -0.60
     Flavoring
    -0.59
     Skydragon
    -0.57
    POSITIVE LOGITS
    urtle
    1.01
    ween
    0.91
    otally
    0.90
    olkien
    0.83
    acular
    0.83
    alion
    0.82
    ruly
    0.82
    ronic
    0.82
    reprene
    0.82
    urtles
    0.82
    Activations Density 0.028%

    No Known Activations