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. 2-RES-JB
    6. 9525
    Prev
    Next
    INDEX
    Explanations

    phrases expressing sympathy or condolences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of sympathy and condolences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Testing
    -0.69
    avery
    -0.68
    alter
    -0.66
    smoking
    -0.66
    agers
    -0.65
    tail
    -0.65
    Myth
    -0.65
    skill
    -0.64
    foot
    -0.63
    adj
    -0.63
    POSITIVE LOGITS
     condolences
    1.17
     acknowled
    0.83
     greet
    0.82
     prayers
    0.76
     saddened
    0.75
     goodbye
    0.74
     thanking
    0.73
     mourn
    0.73
     aloud
    0.72
     THANK
    0.70
    Activations Density 0.008%

    No Known Activations