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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 23648
    Prev
    Next
    INDEX
    Explanations

    phrases where something is being verbally added

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "added" and its variations

    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
    misc
    -0.59
     mathemat
    -0.57
    SPONSORED
    -0.56
    cies
    -0.56
    prototype
    -0.53
    isoft
    -0.53
    Cop
    -0.51
     metic
    -0.50
    asus
    -0.50
     Harbor
    -0.50
    POSITIVE LOGITS
     sarcast
    0.91
     omin
    0.88
     that
    0.82
     insult
    0.81
    :
    0.79
    ictions
    0.78
    itional
    0.78
    itionally
    0.74
    :"
    0.73
     afterwards
    0.72
    Activations Density 0.062%

    No Known Activations