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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 0-RES-JB
    6. 21653
    Prev
    Next
    INDEX
    Explanations

    phrases related to pardoning or forgiving someone or a group of people

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "oned" or related verb forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sah
    -0.61
     surf
    -0.60
     stat
    -0.60
     May
    -0.60
     struggles
    -0.59
     Sturgeon
    -0.59
     slide
    -0.58
     Party
    -0.56
     Cad
    -0.56
     experts
    -0.55
    POSITIVE LOGITS
    oned
    4.56
    oning
    3.36
    ones
    2.03
    onal
    1.92
    onement
    1.80
    oner
    1.76
    ons
    1.45
    onic
    1.40
    ioned
    1.32
    ONES
    1.30
    Activations Density 0.017%

    No Known Activations