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

    Neuronpedia

    Jacobian LensNEW
    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. 4874
    Prev
    Next
    INDEX
    Explanations

    comparisons or likelihood statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to likelihood or probability of events happening

    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
    hai
    -0.78
    quickShipAvailable
    -0.71
    listed
    -0.65
     Sure
    -0.61
    _.
    -0.60
     Elise
    -0.59
     Canary
    -0.59
     Advertisement
    -0.58
    Directory
    -0.58
     reperto
    -0.58
    POSITIVE LOGITS
     be
    1.02
     absorb
    0.92
     revisit
    0.88
     earn
    0.87
    ilers
    0.86
     avoid
    0.85
     spend
    0.82
     engage
    0.82
     pick
    0.81
     stick
    0.81
    Activations Density 0.086%

    No Known Activations