© 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. 6-RES-JB
    11. 9156
    Prev
    Next
    INDEX
    Explanations

    phrases indicating reflective thinking or introspection

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the pronoun "it" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Angola
    -0.63
     Friendly
    -0.62
     Fine
    -0.61
    dding
    -0.60
    idon
    -0.59
    mobile
    -0.59
    Band
    -0.59
    ority
    -0.57
    ggies
    -0.57
    cox
    -0.56
    POSITIVE LOGITS
    alian
    0.94
    chy
    0.87
     transpired
    0.86
    asca
    0.84
     pains
    0.83
     beh
    0.82
    unes
    0.82
     rains
    0.79
     happened
    0.78
     boils
    0.77
    Activations Density 0.123%

    No Known Activations