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. 23547
    Prev
    Next
    INDEX
    Explanations

    instances of the word "mutations."

    oai_token-act-pair · gpt-3.5-turbo

    words related to reputation or its variations

    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
     refuse
    -0.66
     aid
    -0.65
     North
    -0.62
     Helm
    -0.61
     horn
    -0.60
     Cage
    -0.59
     Cly
    -0.59
     aids
    -0.59
     South
    -0.59
     assistance
    -0.59
    POSITIVE LOGITS
    utations
    4.44
    utation
    3.96
    uted
    2.37
    utable
    1.87
    uting
    1.72
    utes
    1.61
    ute
    1.55
    utics
    1.32
    utions
    1.29
    ution
    1.24
    Activations Density 0.014%

    No Known Activations