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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 5-RES-JB
    6. 7800
    Prev
    Next
    INDEX
    Explanations

    highly engaging or attention-grabbing video titles with strong emotional or sensational language

    oai_token-act-pair · gpt-3.5-turbo

    mentions of video content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arious
    -0.81
    bably
    -0.68
    ĺħ
    -0.67
     Classification
    -0.66
     Preservation
    -0.64
    omnia
    -0.64
    orescence
    -0.63
    Ͻ
    -0.63
    ongevity
    -0.63
    idia
    -0.63
    POSITIVE LOGITS
     VIDEOS
    0.80
     IMAGES
    0.76
    iques
    0.74
    å§
    0.71
    natureconservancy
    0.70
     SEN
    0.68
    thumbnails
    0.67
     than
    0.64
    utm
    0.62
    advertisement
    0.61
    Activations Density 0.023%

    No Known Activations