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. 5-RES-JB
    6. 12390
    Prev
    Next
    INDEX
    Explanations

    comparisons or contrasts between two ideas

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating duality or contrasting qualities

    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
    ugu
    -0.83
    lé
    -0.70
    uez
    -0.70
    renheit
    -0.70
    ilit
    -0.67
     Kard
    -0.66
    dq
    -0.65
    acion
    -0.64
    lus
    -0.63
    lic
    -0.63
    POSITIVE LOGITS
     sexes
    1.50
     sides
    1.31
     halves
    1.26
     genders
    1.23
     thirds
    0.83
    ocating
    0.81
     ends
    0.78
     senses
    0.75
     parties
    0.74
     kinds
    0.73
    Activations Density 0.052%

    No Known Activations