© 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. 11-RES-JB
    11. 5184
    Prev
    Next
    INDEX
    Explanations

    second person pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo
    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
     è£ıè¦ļéĨĴ
    -0.73
     doesnt
    -0.66
    Secondly
    -0.66
     [/
    -0.62
    [/
    -0.62
    Mech
    -0.62
    FX
    -0.61
    Firstly
    -0.60
    However
    -0.60
     behavi
    -0.60
    POSITIVE LOGITS
     crave
    0.98
     fret
    0.89
     recite
    0.88
     envision
    0.87
     worry
    0.86
     weep
    0.86
     shrug
    0.86
     hesitate
    0.84
     contemplate
    0.84
     breathe
    0.83
    Activations Density 0.703%

    No Known Activations