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. 24216
    Prev
    Next
    INDEX
    Explanations

    instances where the text discusses speaking or conveying a message

    oai_token-act-pair · gpt-3.5-turbo

    expressions of speaking or communicating, particularly about personal or shared experiences

    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
    gradation
    -0.71
     additions
    -0.70
     rolls
    -0.68
    20439
    -0.66
     Released
    -0.64
     Expend
    -0.63
    hesda
    -0.62
    dating
    -0.61
     Landing
    -0.60
    adelphia
    -0.59
    POSITIVE LOGITS
     louder
    0.89
    plain
    0.80
     deaf
    0.79
     loudly
    0.78
     voic
    0.78
     speaker
    0.78
    aram
    0.70
     TED
    0.70
     CNBC
    0.70
    ference
    0.69
    Activations Density 0.135%

    No Known Activations