© 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. 4-RES-JB
    11. 5112
    Prev
    Next
    INDEX
    Explanations

    Latin-rooted words ending in 's'

    oai_token-act-pair · gpt-3.5-turbo

    the letter 's' at varying frequencies, indicating a focus on plural forms or specific pluralized terms

    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
    £ı
    -0.72
     Leilan
    -0.69
    quickShipAvailable
    -0.66
    electric
    -0.66
    FINE
    -0.65
    ONSORED
    -0.63
    LEASE
    -0.63
     Nep
    -0.59
     ALP
    -0.59
     fuss
    -0.59
    POSITIVE LOGITS
    ources
    1.25
    ouls
    1.13
    ourced
    1.10
    kaya
    1.08
    ourcing
    1.07
    atisf
    1.04
    ales
    1.02
    uns
    1.01
    acks
    1.00
    ustain
    1.00
    Activations Density 0.178%

    No Known Activations