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. 7447
    Prev
    Next
    INDEX
    Explanations

    words related to advocacy and support

    oai_token-act-pair · gpt-3.5-turbo

    mentions of advocacy and advocates for various causes or groups

    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
     Tsukuyomi
    -0.64
    plet
    -0.64
     Strait
    -0.62
     gorge
    -0.61
    bum
    -0.60
    seed
    -0.60
    kered
    -0.59
    peg
    -0.58
     Carbuncle
    -0.58
     Hath
    -0.58
    POSITIVE LOGITS
     advocating
    0.79
    acy
    0.75
    iatrics
    0.71
     advocate
    0.70
    ģĸ
    0.67
    ="#
    0.67
    atives
    0.66
    iants
    0.66
     advocates
    0.66
     advocacy
    0.65
    Activations Density 0.026%

    No Known Activations