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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 17687
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussing or resolving a situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve the concept of putting something to rest or use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scl
    -0.64
    etheless
    -0.63
    nox
    -0.62
    legged
    -0.61
    ÃŁ
    -0.60
    aucas
    -0.60
     Cavern
    -0.59
    emonium
    -0.59
    hex
    -0.58
    xd
    -0.58
    POSITIVE LOGITS
     jeopardy
    0.69
     certs
    0.63
    âĢİ
    0.63
     aside
    0.62
     Saud
    0.61
    à¨
    0.59
     Wendy
    0.59
     shame
    0.58
    rolled
    0.58
    RAG
    0.57
    Activations Density 0.099%

    No Known Activations