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. 14463
    Prev
    Next
    INDEX
    Explanations

    phrases related to coercion or manipulation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating coercion or manipulation

    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
     corpus
    -0.72
    thora
    -0.69
    ghai
    -0.65
    ometimes
    -0.64
    terday
    -0.63
    etheless
    -0.61
    yip
    -0.61
     capacitor
    -0.61
    hetically
    -0.60
    EMP
    -0.59
    POSITIVE LOGITS
     adulthood
    0.93
     submission
    0.89
    jection
    0.77
     Valhalla
    0.76
     ob
    0.71
     adolescence
    0.70
    clusion
    0.70
    addon
    0.67
     existence
    0.66
     exile
    0.65
    Activations Density 0.056%

    No Known Activations