© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 11862
    Prev
    Next
    INDEX
    Explanations

    sentences containing the word "yes" followed by personal pronouns and verbs indicating action or belief

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns and expressions of personal sentiment or belief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Merit
    -0.74
    orer
    -0.71
     )]
    -0.70
    instead
    -0.70
    -+
    -0.69
    livious
    -0.69
    assembly
    -0.66
    Hide
    -0.65
    é¾įå¥ij士
    -0.65
    liness
    -0.65
    POSITIVE LOGITS
     DID
    0.84
     lied
    0.81
     existed
    0.80
     technically
    0.77
     indeed
    0.71
     cried
    0.69
     correct
    0.68
     exist
    0.68
     theoretically
    0.68
     qualifies
    0.67
    Activations Density 0.205%

    No Known Activations