© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 400
    Prev
    Next
    INDEX
    Explanations

    references to "Cry" or "cry" in the context of different scenarios like cryptocurrency, emotions, or actions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of cryptocurrency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    velength
    -0.71
    aughs
    -0.68
     nomine
    -0.67
     POLIT
    -0.65
    ****************
    -0.62
     Mandela
    -0.62
    «ĺ
    -0.61
    committee
    -0.61
     priv
    -0.60
    ++++
    -0.60
    POSITIVE LOGITS
    stals
    1.67
    sis
    1.26
    pter
    1.23
    stal
    1.23
    stall
    1.21
    ogen
    0.95
    onics
    0.88
    ogenic
    0.84
    Cry
    0.84
    rine
    0.84
    Activations Density 0.008%

    No Known Activations