© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 584
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a future action or time reference

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "later on."

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

    No Comments

    Negative Logits
    MODE
    -0.78
    CHAT
    -0.70
    SourceFile
    -0.70
    SIM
    -0.69
    RL
    -0.68
    Allah
    -0.68
    Bey
    -0.66
    BIP
    -0.65
    SHARE
    -0.64
    9999
    -0.64
    POSITIVE LOGITS
    etime
    1.09
     behalf
    1.04
    shore
    1.00
    erous
    0.90
    demand
    0.90
     occasion
    0.88
    eness
    0.87
    slaught
    0.85
    essee
    0.85
     average
    0.84
    Activations Density 0.225%

    No Known Activations