© 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. 2-RES-JB
    11. 3164
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic recessions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to "sessions."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deceased
    -0.65
     à¤
    -0.62
     procedural
    -0.60
    ACTED
    -0.60
     foreseeable
    -0.59
     elephant
    -0.59
    INAL
    -0.58
     Tau
    -0.58
    protein
    -0.57
     organizational
    -0.57
    POSITIVE LOGITS
    essions
    1.16
    ession
    0.95
    hots
    0.80
    hare
    0.75
    uality
    0.74
    iership
    0.73
    erness
    0.73
    yne
    0.73
    ynamic
    0.71
    igent
    0.70
    Activations Density 0.016%

    No Known Activations