© 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. 10008
    Prev
    Next
    INDEX
    Explanations

    terms related to supporting or opposing something through a particular stance, typically starting with 'pro'

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of 'pro' or support for a specific cause or ideology

    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
    ãĤ¼ãĤ¦ãĤ¹
    -0.67
     afar
    -0.67
     numb
    -0.59
     fault
    -0.59
     silence
    -0.59
     blindness
    -0.56
     Twain
    -0.56
     wasteland
    -0.55
    hips
    -0.55
     fate
    -0.55
    POSITIVE LOGITS
    blems
    1.58
    gressive
    1.52
    ceed
    1.46
    secut
    1.42
    bable
    1.35
    spective
    1.34
    posal
    1.31
    portion
    1.31
    hibition
    1.27
    testers
    1.27
    Activations Density 0.017%

    No Known Activations