© 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. 7-RES-JB
    11. 22825
    Prev
    Next
    INDEX
    Explanations

    the word "openly" used in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "openly" in various contexts related to self-disclosure and identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesota
    -0.86
     Tune
    -0.74
    ĸļ
    -0.74
    oday
    -0.71
    =-=-=-=-=-=-=-=-
    -0.69
     Summoner
    -0.68
    ocre
    -0.67
     unnecess
    -0.67
    UTE
    -0.64
     Millennium
    -0.64
    POSITIVE LOGITS
     admit
    0.80
     admitted
    0.80
     defied
    0.80
     bisexual
    0.79
     confess
    0.79
     openly
    0.78
     contradicted
    0.78
     admits
    0.77
     acknowledged
    0.77
     profess
    0.77
    Activations Density 0.031%

    No Known Activations