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. 2-RES-JB
    6. 20280
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial payouts

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to financial assistance or government bailouts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wake
    -0.59
    UTERS
    -0.59
     Dak
    -0.59
     fabrication
    -0.58
    RET
    -0.57
    EMBER
    -0.56
     oxid
    -0.56
     Realm
    -0.55
    THER
    -0.54
     Phi
    -0.54
    POSITIVE LOGITS
    doors
    0.99
    paces
    0.98
    weet
    0.93
    outs
    0.90
    hips
    0.89
    pace
    0.87
    lash
    0.85
    stretched
    0.83
    ourcing
    0.83
    iders
    0.83
    Activations Density 0.010%

    No Known Activations