Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 17364
    Prev
    Next
    INDEX
    Explanations

    the word "strive" or its variations

    oai_token-act-pair · gpt-3.5-turbo

    repeated usage of the word "strive" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     emergency
    -0.79
    ocket
    -0.74
     panic
    -0.73
    spot
    -0.71
     timing
    -0.69
    fect
    -0.69
     Gas
    -0.68
     cancellation
    -0.67
    cox
    -0.67
    Emergency
    -0.67
    POSITIVE LOGITS
     strive
    2.71
     aspire
    2.49
     striving
    2.42
     strives
    2.10
     aspiring
    1.85
     adhere
    1.66
     endeavor
    1.44
     stri
    1.41
     abide
    1.39
     endeavour
    1.38
    Activations Density 0.062%

    No Known Activations