Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 11874
    Prev
    Next
    INDEX
    Explanations

    strong negative descriptors or dire situations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "severe" and its context, particularly related to various critical situations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tein
    -0.82
    ynthesis
    -0.81
    hops
    -0.78
    xxxxxxxx
    -0.76
    atography
    -0.76
    rium
    -0.74
    ramid
    -0.74
    pire
    -0.73
    rious
    -0.72
    neapolis
    -0.72
    POSITIVE LOGITS
     earthqu
    1.01
     severity
    0.94
     severe
    0.89
     consequences
    0.88
     distress
    0.86
     punishments
    0.84
     conflic
    0.82
     allergic
    0.80
     repercussions
    0.80
     injury
    0.80
    Activations Density 0.013%

    No Known Activations