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. 8-RES-JB
    6. 5426
    Prev
    Next
    INDEX
    Explanations

    phrases containing words expressing contrast

    oai_token-act-pair · gpt-3.5-turbo

    repetitive use of "the" to emphasize significance or detail

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     followed
    -0.71
    iguous
    -0.68
    %%%%
    -0.68
    esh
    -0.66
    eton
    -0.65
    Split
    -0.62
    Chain
    -0.62
    together
    -0.61
    iac
    -0.61
     Albania
    -0.60
    POSITIVE LOGITS
     extent
    1.56
     fullest
    1.22
     detriment
    1.22
     tune
    1.11
     same
    1.07
     nearest
    1.02
    rouse
    1.01
     exclusion
    0.98
     forefront
    0.97
    venge
    0.97
    Activations Density 0.222%

    No Known Activations