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. 7-RES-JB
    6. 20270
    Prev
    Next
    INDEX
    Explanations

    sentences indicating a necessity for action or resolution

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the necessity for action or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Guilty
    -0.69
     Zip
    -0.66
    gdala
    -0.65
     Pill
    -0.62
     Rost
    -0.62
    SHIP
    -0.59
     âĨij
    -0.59
    izon
    -0.58
    ulty
    -0.58
    dylib
    -0.58
    POSITIVE LOGITS
    lessly
    1.03
    FINE
    0.87
     attention
    0.80
    orters
    0.76
     precedence
    0.72
     scrutiny
    0.72
    lest
    0.72
     clarification
    0.67
    ILY
    0.64
     consideration
    0.64
    Activations Density 0.075%

    No Known Activations