© 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
    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. 7838
    Prev
    Next
    INDEX
    Explanations

    phrases related to official statements or documents

    oai_token-act-pair · gpt-3.5-turbo

    phrases and constructs involving "statements of."

    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
    ãĤ¼ãĤ¦ãĤ¹
    -0.73
    ÃŁ
    -0.71
    Enlarge
    -0.68
     ItemLevel
    -0.67
    zers
    -0.64
     Flavoring
    -0.63
    atoes
    -0.63
    perture
    -0.63
     Dise
    -0.62
     grin
    -0.61
    POSITIVE LOGITS
     course
    0.84
     arbitration
    0.76
     sorts
    0.70
     inquiry
    0.67
     truce
    0.67
    angible
    0.67
     Inquiry
    0.66
    writ
    0.65
    sted
    0.65
     condol
    0.64
    Activations Density 0.360%

    No Known Activations