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

    Neuronpedia

    APICircuit 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. 6-RES-JB
    6. 21349
    Prev
    Next
    INDEX
    Explanations

    words related to being overwhelmed or heavily influenced by something

    oai_token-act-pair · gpt-3.5-turbo

    words associated with overwhelming or excessive situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     srfAttach
    -0.90
    IFF
    -0.66
    strength
    -0.64
    peer
    -0.63
    uber
    -0.62
     rapp
    -0.62
    NOR
    -0.62
    stop
    -0.61
    quickShipAvailable
    -0.60
    reme
    -0.60
    POSITIVE LOGITS
    iously
    0.87
     inbox
    0.82
    agues
    0.76
    attery
    0.74
     waters
    0.74
    uzz
    0.73
    ciating
    0.72
     coats
    0.71
    issance
    0.70
    odies
    0.70
    Activations Density 0.141%

    No Known Activations