© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    6. 5224
    Prev
    Next
    INDEX
    Explanations

    phrases expressing a strong position or stance on a particular issue or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "standing" or being upright, both physically and metaphorically

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    via
    -0.73
    idine
    -0.70
    mails
    -0.69
     Via
    -0.66
    Information
    -0.61
    DATA
    -0.61
     DeVos
    -0.60
    osis
    -0.60
     Analytics
    -0.59
     Freed
    -0.59
    POSITIVE LOGITS
     stand
    3.72
     Stand
    2.35
     stands
    2.23
    stand
    2.21
    Stand
    2.09
     stood
    1.78
     STAND
    1.61
     sit
    1.53
     standing
    1.44
    stood
    1.26
    Activations Density 0.012%

    No Known Activations