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. 15831
    Prev
    Next
    INDEX
    Explanations

    the word "def" or variations of it: "defected", "defense", or "defined"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "defame" or its derivatives

    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
    DAY
    -0.77
     Dragonbound
    -0.72
     Bohem
    -0.71
    externalActionCode
    -0.66
     Madness
    -0.66
     Archdemon
    -0.65
     Hour
    -0.65
     Observatory
    -0.65
     Boll
    -0.64
     [|
    -0.64
    POSITIVE LOGITS
    ensible
    1.23
    ibr
    1.17
    erent
    1.03
    acement
    1.02
    anged
    1.02
    erence
    0.98
    ected
    0.98
    ident
    0.98
    aul
    0.97
    ensions
    0.96
    Activations Density 0.008%

    No Known Activations