© 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
    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. 9106
    Prev
    Next
    INDEX
    Explanations

    phrases related to time span

    oai_token-act-pair · gpt-3.5-turbo

    phrases that frequently include the word "rest" in various contexts

    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
     Ear
    -0.63
     Dice
    -0.59
     Oy
    -0.58
     Yamato
    -0.57
     Speedway
    -0.57
     Mahjong
    -0.56
     Gemini
    -0.56
     insin
    -0.55
     TRUMP
    -0.54
    FK
    -0.53
    POSITIVE LOGITS
    ructure
    1.08
    orative
    1.04
    raint
    1.02
    raints
    0.86
     newcom
    0.82
    owment
    0.78
    oleon
    0.78
    rats
    0.77
    retched
    0.76
    hetically
    0.76
    Activations Density 0.013%

    No Known Activations