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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 15869
    Prev
    Next
    INDEX
    Explanations

    words related to names of people or characters

    oai_token-act-pair · gpt-3.5-turbo

    words associated with the name "Thad Cochran" and related references

    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
    lished
    -0.76
    âĢ¢âĢ¢
    -0.75
    é¾
    -0.66
    ãĤ±
    -0.65
    ãĥĨ
    -0.64
    ãĤ¦
    -0.63
    ãĥĩ
    -0.63
    ENC
    -0.62
     kcal
    -0.60
    Spons
    -0.59
    POSITIVE LOGITS
    issan
    0.81
    mort
    0.80
    inge
    0.77
    acket
    0.73
    ttle
    0.72
    iasis
    0.69
    mology
    0.67
    bush
    0.66
    way
    0.66
    ung
    0.66
    Activations Density 0.076%

    No Known Activations