© 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. 8-RES-JB
    6. 7142
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and evaluation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the necessity for evaluation or decision-making based on evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zie
    -0.76
    ciating
    -0.74
    izen
    -0.73
    ĺħ
    -0.72
    ãĤ§
    -0.70
    \\\\\\\\\\\\\\\\
    -0.70
     Eater
    -0.69
    izens
    -0.68
    quickShipAvailable
    -0.67
    facts
    -0.67
    POSITIVE LOGITS
     reinstated
    1.07
     recomm
    1.06
     postp
    1.02
     disqual
    1.01
     proceed
    1.01
     restart
    1.00
     adjourn
    1.00
    Continue
    0.97
     reconsider
    0.96
     shel
    0.93
    Activations Density 1.082%

    No Known Activations