© 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 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. 9-RES-JB
    11. 19865
    Prev
    Next
    INDEX
    Explanations

    instances where the word "try" is followed by another verb or adverb

    oai_token-act-pair · gpt-3.5-turbo

    instances of attempts or efforts related to actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Kings
    -0.71
    Gab
    -0.67
    gren
    -0.67
    abul
    -0.65
    ullah
    -0.62
    rome
    -0.61
    Installation
    -0.61
    LOAD
    -0.60
    electric
    -0.59
    rower
    -0.57
    POSITIVE LOGITS
     valiant
    0.96
     diligently
    0.88
     minimize
    0.87
     emphas
    0.79
     careful
    0.78
     tirelessly
    0.78
     hardest
    0.78
     not
    0.76
     relentlessly
    0.75
     vigorously
    0.75
    Activations Density 0.154%

    No Known Activations