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. 2775
    Prev
    Next
    INDEX
    Explanations

    names related to characters or places, identified through repetitions of words

    oai_token-act-pair · gpt-3.5-turbo

    references to the title "The Sound and the Fury."

    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
    pocket
    -0.77
    izational
    -0.77
    organic
    -0.76
    esthetic
    -0.76
    opathy
    -0.75
    kai
    -0.74
    mers
    -0.74
     quo
    -0.73
    repeat
    -0.73
    ership
    -0.71
    POSITIVE LOGITS
     Fury
    0.97
    anche
    0.82
    ricanes
    0.80
     tremend
    0.74
     FC
    0.73
    rites
    0.72
    anches
    0.71
    ous
    0.70
    auld
    0.69
    raviolet
    0.69
    Activations Density 0.021%

    No Known Activations