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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 485
    Prev
    Next
    INDEX
    Explanations

    specific words expressing urgency or importance

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with urgent requests and pleas for action

    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
     NX
    -0.68
    miah
    -0.65
     Siber
    -0.64
     Wink
    -0.64
     Surv
    -0.62
     Seym
    -0.60
     Cheong
    -0.59
     Sax
    -0.59
    ascript
    -0.59
    vae
    -0.59
    POSITIVE LOGITS
     begging
    0.80
     forgiveness
    0.75
    naires
    0.69
     urging
    0.66
     forgive
    0.66
    Submit
    0.65
     bargain
    0.65
     seeking
    0.65
     to
    0.65
     compulsion
    0.65
    Activations Density 0.211%

    No Known Activations