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. 13718
    Prev
    Next
    INDEX
    Explanations

    words related to persuasion or influence

    oai_token-act-pair · gpt-3.5-turbo

    words related to persuasion and influence

    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
     Dock
    -0.68
    uben
    -0.65
     dotted
    -0.64
     reckoning
    -0.62
    andro
    -0.62
    ©¶æ
    -0.59
     Antiqu
    -0.59
    çĦ
    -0.58
     sequ
    -0.57
    arna
    -0.57
    POSITIVE LOGITS
    pter
    0.85
     audiences
    0.81
    ingly
    0.78
     gull
    0.78
    GGGGGGGG
    0.75
    eer
    0.73
    MENT
    0.71
    advertising
    0.70
    imaru
    0.70
     moderates
    0.70
    Activations Density 0.219%

    No Known Activations