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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 4458
    Prev
    Next
    INDEX
    Explanations

    adjectives related to personal qualities and behavior

    oai_token-act-pair · gpt-3.5-turbo

    words associated with positive attributes and emotional intelligence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ô
    -0.86
    ciation
    -0.65
    swick
    -0.63
    è£ħ
    -0.62
     insign
    -0.61
    åĪ
    -0.59
    oval
    -0.57
    vertisement
    -0.57
     Byrd
    -0.56
     reconciliation
    -0.56
    POSITIVE LOGITS
     minded
    0.89
    looking
    0.84
     thinkers
    0.81
     discipl
    0.81
     towards
    0.80
     learners
    0.75
     thinker
    0.74
     defensively
    0.73
     toward
    0.73
    ceptive
    0.73
    Activations Density 0.270%

    No Known Activations