© 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. 13989
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing uncertainty, opinion, or knowledge

    oai_token-act-pair · gpt-3.5-turbo

    affirmations and expressions of agreement

    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
    士
    -0.70
    ©¶æ
    -0.70
    andon
    -0.68
    chuk
    -0.64
    atel
    -0.62
    angan
    -0.62
    acci
    -0.61
    igree
    -0.60
    rehend
    -0.60
    iff
    -0.60
    POSITIVE LOGITS
    cause
    0.69
    JV
    0.68
     dunno
    0.64
     effic
    0.63
    ãĤĵ
    0.63
    othe
    0.62
     ********************************
    0.62
     congr
    0.60
     glim
    0.58
     craw
    0.58
    Activations Density 0.521%

    No Known Activations