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. 2545
    Prev
    Next
    INDEX
    Explanations

    the word "swear" and variations of it in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "swear" and its variations, indicating discussions about swearing and its implications

    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
    å§«
    -0.86
    DragonMagazine
    -0.85
    èĥ
    -0.84
    Vert
    -0.76
    issues
    -0.70
    NetMessage
    -0.69
     guiActiveUnfocused
    -0.69
    OTOS
    -0.68
    Kin
    -0.68
    EMS
    -0.68
    POSITIVE LOGITS
     swear
    1.13
     oath
    1.10
     swearing
    1.03
     swore
    0.99
     vow
    0.93
     sworn
    0.81
     allegiance
    0.78
    words
    0.74
     falsely
    0.74
    kowski
    0.74
    Activations Density 0.016%

    No Known Activations