© 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. 1-RES-JB
    11. 16781
    Prev
    Next
    INDEX
    Explanations

    words related to materials or items made of plastic

    oai_token-act-pair · gpt-3.5-turbo

    words related to various styles and types of materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     WARN
    -0.77
     Immunity
    -0.71
     VIDEOS
    -0.71
     Pioneer
    -0.71
     THR
    -0.70
    ajor
    -0.70
     Butterfly
    -0.69
     Leap
    -0.66
     Humanity
    -0.64
     Victims
    -0.64
    POSITIVE LOGITS
    sty
    1.56
    rette
    0.91
    rene
    0.90
    led
    0.87
    les
    0.81
    rous
    0.80
    fab
    0.78
    gae
    0.78
    lys
    0.77
    gian
    0.76
    Activations Density 0.006%

    No Known Activations