© 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. 14826
    Prev
    Next
    INDEX
    Explanations

    the word "just" emphasized for emphasis or significance

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of "more than just" something, highlighting complexity or depth in a subject

    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
    sembly
    -0.74
    ccording
    -0.68
     Remastered
    -0.68
    lav
    -0.68
    ĺħ
    -0.67
     challeng
    -0.65
     Huck
    -0.64
    endra
    -0.62
    lass
    -0.61
    insula
    -0.60
    POSITIVE LOGITS
    ifiable
    1.32
    ifications
    1.10
    ifiers
    0.87
    ified
    0.86
    ifying
    0.86
    ifi
    0.84
    icia
    0.84
    ification
    0.83
    ifier
    0.82
    ices
    0.80
    Activations Density 0.078%

    No Known Activations