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. 9-RES-JB
    6. 2181
    Prev
    Next
    INDEX
    Explanations

    instances where someone is encouraging others to come forward with information or experiences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Goo
    -0.64
    @@@@@@@@
    -0.62
    ĺħ
    -0.61
    Pattern
    -0.60
     pleasure
    -0.59
    rpm
    -0.58
    icion
    -0.58
    ptions
    -0.57
     Sent
    -0.57
    ©
    -0.56
    POSITIVE LOGITS
     voluntarily
    1.04
     anonymously
    0.90
    onyms
    0.81
     publicly
    0.77
     willingly
    0.77
     alleging
    0.77
     unsc
    0.70
     spontaneously
    0.68
     accusing
    0.68
     claiming
    0.68
    Activations Density 0.054%

    No Known Activations