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. 4-RES-JB
    6. 8719
    Prev
    Next
    INDEX
    Explanations

    proper nouns where someone is appointed to a specific position or role

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "appointed"

    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
    patch
    -0.89
    olver
    -0.74
    fal
    -0.68
    λ
    -0.68
    ijn
    -0.66
    psc
    -0.64
     degrade
    -0.63
    Pear
    -0.62
    iday
    -0.60
    brance
    -0.60
    POSITIVE LOGITS
     appoint
    0.96
     appointed
    0.92
     appointments
    0.86
    ancies
    0.84
    eering
    0.80
     appointing
    0.79
    ees
    0.78
     "$:/
    0.78
     appointment
    0.76
     commissions
    0.75
    Activations Density 0.020%

    No Known Activations