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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 23096
    Prev
    Next
    INDEX
    Explanations

    references to the New York Times

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to New York Times newsletters

    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
     Greenberg
    -0.64
    Occ
    -0.64
    XL
    -0.64
    abase
    -0.63
    ello
    -0.63
    igl
    -0.63
     Shank
    -0.63
    aimon
    -0.62
    undown
    -0.62
    uca
    -0.61
    POSITIVE LOGITS
     infringing
    0.65
     except
    0.62
     captcha
    0.62
    ################
    0.62
     captures
    0.61
     trave
    0.61
     executions
    0.60
     videos
    0.60
     emails
    0.60
     Terms
    0.59
    Activations Density 0.036%

    No Known Activations