© 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. 11-RES-JB
    6. 9462
    Prev
    Next
    INDEX
    Explanations

    future projections and estimates

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating future possibilities or projections

    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
    soType
    -1.09
    quickShipAvailable
    -0.84
    quished
    -0.58
     Palest
    -0.58
    foreseen
    -0.57
     Aden
    -0.56
    IME
    -0.56
     Relations
    -0.56
     Rebell
    -0.56
     validation
    -0.56
    POSITIVE LOGITS
     exceed
    1.16
     reach
    1.09
     overtake
    1.09
     generate
    1.05
     lose
    1.03
     achieve
    1.03
     earn
    1.03
     consume
    1.03
     surpass
    1.02
     comprise
    1.01
    Activations Density 0.129%

    No Known Activations