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. 11758
    Prev
    Next
    INDEX
    Explanations

    conclusion or continuation signals in written text

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Article Continued Below."

    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
    aceae
    -0.75
    utic
    -0.74
    umenthal
    -0.73
     honor
    -0.70
    channelAvailability
    -0.69
    rams
    -0.69
    ãĤ©
    -0.69
    ids
    -0.68
    ãĤ·ãĥ£
    -0.66
    caps
    -0.65
    POSITIVE LOGITS
     Continued
    0.98
     Harbour
    0.81
     Below
    0.76
     Cheong
    0.76
     VIDEOS
    0.74
     Provided
    0.73
     Applicant
    0.70
     Ancients
    0.69
    shire
    0.69
     Territories
    0.68
    Activations Density 0.015%

    No Known Activations