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. 7-RES-JB
    6. 9065
    Prev
    Next
    INDEX
    Explanations

    words related to responsibilities or obligations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "duty" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ergy
    -0.73
    iques
    -0.71
    anz
    -0.70
     Lans
    -0.69
    alph
    -0.68
    vae
    -0.68
     Juliet
    -0.64
    quart
    -0.64
    hetti
    -0.63
    upt
    -0.63
    POSITIVE LOGITS
     Duty
    1.03
     duty
    1.00
    uty
    1.00
    duty
    0.94
     duties
    0.80
    uties
    0.76
     station
    0.74
     refres
    0.72
     obligation
    0.69
    IELD
    0.69
    Activations Density 0.022%

    No Known Activations