© 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. 18750
    Prev
    Next
    INDEX
    Explanations

    phrases that contain hypens and slashes

    oai_token-act-pair · gpt-3.5-turbo

    negative statements or phrases expressing disbelief or denial

    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
     watches
    -0.73
     boarding
    -0.73
     adm
    -0.67
     Lancaster
    -0.65
     trusting
    -0.65
     chatting
    -0.65
     chats
    -0.61
     clothed
    -0.61
     convers
    -0.60
     supervised
    -0.59
    POSITIVE LOGITS
    tain
    1.12
    mean
    1.05
    uable
    1.04
    exist
    1.00
    t
    0.96
    tale
    0.88
    olve
    0.87
    ãĤ¡
    0.84
    tion
    0.84
    require
    0.83
    Activations Density 0.160%

    No Known Activations