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. 11-RES-JB
    6. 3929
    Prev
    Next
    INDEX
    Explanations

    action verbs related to digital tasks and problem-solving

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to transactions and issues in data handling

    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
    knit
    -0.89
     thrive
    -0.71
     inspires
    -0.69
    velt
    -0.68
    clad
    -0.67
    lect
    -0.67
    cknow
    -0.67
    conom
    -0.66
    soever
    -0.64
     emerges
    -0.64
    POSITIVE LOGITS
     incorrect
    1.65
     wrong
    1.37
     insufficient
    1.35
     inaccurate
    1.33
     unsu
    1.33
     erroneous
    1.30
     incorrectly
    1.29
     improper
    1.28
     invalid
    1.27
     faulty
    1.26
    Activations Density 0.634%

    No Known Activations