© 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. 11-RES-JB
    6. 503
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific company brand starting with the letter "V"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific television channels or networks

    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
     something
    -0.64
     writ
    -0.62
     unrestricted
    -0.62
     Rampage
    -0.61
    ¯¯
    -0.59
     Jur
    -0.59
     resolving
    -0.58
     AAA
    -0.57
     persu
    -0.57
     named
    -0.56
    POSITIVE LOGITS
    arsity
    1.38
    oodoo
    1.37
    ulture
    1.29
    antage
    1.26
    odka
    1.25
    isions
    1.23
    ISION
    1.22
    ampires
    1.21
    IRT
    1.20
    imeo
    1.20
    Activations Density 0.026%

    No Known Activations