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. 1-RES-JB
    6. 8174
    Prev
    Next
    INDEX
    Explanations

    words related to expressing sorrow or regret

    oai_token-act-pair · gpt-3.5-turbo

    expressions of grief or regret

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 1 - sadness

    No Comments

    Negative Logits
    fighters
    -0.80
    testers
    -0.76
    cius
    -0.75
    ammy
    -0.74
    istration
    -0.72
    eared
    -0.72
    friends
    -0.71
    raviolet
    -0.70
    fighter
    -0.69
    emouth
    -0.69
    POSITIVE LOGITS
     lament
    1.13
     lamented
    0.88
     Coliseum
    0.81
    ãģ®éŃĶ
    0.78
    70710
    0.74
    ãĤ¢ãĥ«
    0.73
    ably
    0.73
    IGN
    0.72
     Canaver
    0.71
    ãĥĸ
    0.71
    Activations Density 0.028%

    No Known Activations