© 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. 11-RES-JB
    11. 18637
    Prev
    Next
    INDEX
    Explanations

    specific phrases or words related to attributing names and terms

    oai_token-act-pair · gpt-3.5-turbo

    topics related to names and designations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VIDEO
    -0.73
    MORE
    -0.71
    OTHER
    -0.64
    HCR
    -0.62
    Government
    -0.60
    PHOTOS
    -0.60
    SIGN
    -0.59
    DAY
    -0.58
    ļéĨĴ
    -0.58
    YE
    -0.58
    POSITIVE LOGITS
     this
    1.21
     these
    1.17
    these
    0.90
     them
    0.89
     him
    0.88
    this
    0.85
     it
    0.83
     THESE
    0.82
     THIS
    0.78
     hers
    0.75
    Activations Density 0.831%

    No Known Activations