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. 10-RES-JB
    6. 22995
    Prev
    Next
    INDEX
    Explanations

    mentions of actions taken by people in various situations, such as being arrested, receiving compliments, reading articles, and expressing displeasure

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $.
    -0.66
    %.
    -0.59
     };
    -0.59
    ;}
    -0.55
    _.
    -0.55
    +.
    -0.54
    }.
    -0.54
    %;
    -0.53
    .;
    -0.51
    .</
    -0.51
    POSITIVE LOGITS
     regarding
    0.79
    osponsors
    0.77
     lately
    0.74
     nowadays
    0.71
     relating
    0.66
    ento
    0.66
     here
    0.62
     herein
    0.62
     Regarding
    0.62
    buquerque
    0.61
    Activations Density 0.902%

    No Known Activations