© 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. 4-RES-JB
    6. 16292
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or consequences taking place after a triggering event

    oai_token-act-pair · gpt-3.5-turbo

    phrases or expressions that indicate a sequence of events or consequences

    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
    esse
    -0.78
    ription
    -0.72
    taboola
    -0.72
    MX
    -0.71
    entric
    -0.70
    istry
    -0.69
     gravy
    -0.68
    tesy
    -0.68
    utical
    -0.67
    illac
    -0.66
    POSITIVE LOGITS
     Hurricane
    0.92
     hostilities
    0.83
     hearing
    0.69
    ricane
    0.69
     adversity
    0.67
     Katrina
    0.66
     impending
    0.65
     storms
    0.65
     Tropical
    0.64
     encountering
    0.64
    Activations Density 0.095%

    No Known Activations