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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15213
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "on" followed by a specific word or phrase

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "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
    ONSORED
    -0.60
    MODE
    -0.58
    SourceFile
    -0.57
    Allah
    -0.55
    âĵĺ
    -0.55
    Champ
    -0.55
    JJ
    -0.55
    ãĥ¯ãĥ³
    -0.54
    2500
    -0.54
    ACT
    -0.54
    POSITIVE LOGITS
     behalf
    1.26
    shore
    0.92
    etime
    0.86
    coming
    0.84
    erous
    0.81
    yx
    0.78
    eness
    0.77
    slaught
    0.76
    demand
    0.76
     occasion
    0.74
    Activations Density 0.264%

    No Known Activations