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. 21694
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Cry" or words related to it, possibly in the context of cryptocurrency or emotional expression

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "cry" in various contexts

    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
     nomine
    -0.71
    velength
    -0.69
     Mandela
    -0.67
    aughs
    -0.67
     priv
    -0.66
    \-
    -0.65
    committee
    -0.65
    ^^^^
    -0.65
     POLIT
    -0.64
    ities
    -0.62
    POSITIVE LOGITS
    stals
    1.66
    stal
    1.26
    stall
    1.24
    sis
    1.19
    pter
    1.18
    ogen
    0.94
    onics
    0.91
    onic
    0.85
    plin
    0.84
    baby
    0.83
    Activations Density 0.012%

    No Known Activations