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. 11-RES-JB
    6. 22894
    Prev
    Next
    INDEX
    Explanations

    words related to emergency or sudden critical situations

    oai_token-act-pair · gpt-3.5-turbo

    words related to emergency situations or conditions

    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
     mileage
    -0.79
     burden
    -0.65
     stub
    -0.63
     cooker
    -0.60
     taunt
    -0.60
     negotiators
    -0.59
     shack
    -0.59
     Sacrifice
    -0.58
     mas
    -0.57
     absor
    -0.57
    POSITIVE LOGITS
    gent
    1.65
    itus
    1.58
    gence
    1.48
    gency
    1.46
    gencies
    1.41
    gently
    1.39
    ging
    1.17
    ges
    1.16
    ald
    1.10
    ge
    1.08
    Activations Density 0.053%

    No Known Activations