© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 704
    Prev
    Next
    INDEX
    Explanations

    words ending with the suffix "ified" or containing "ify"

    oai_token-act-pair · gpt-4-turbo

    phrases related to transformation or change

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of making something official or established

    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
    kers
    -0.74
    noon
    -0.74
    dimension
    -0.72
    ker
    -0.71
    bill
    -0.70
    issue
    -0.67
    album
    -0.65
    riter
    -0.65
    bil
    -0.64
    ngth
    -0.62
    POSITIVE LOGITS
    ification
    1.20
    ify
    1.06
    ifies
    1.05
    ifications
    1.01
    utical
    0.98
    ified
    0.97
    ifiers
    0.95
    ifying
    0.93
    ific
    0.88
    ifier
    0.84
    Activations Density 0.025%

    No Known Activations