© 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. 9-RES-JB
    11. 2624
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Before"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote anticipation or preparatory actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geist
    -0.83
    aternity
    -0.74
    VERTISEMENT
    -0.67
    ologic
    -0.65
    ARS
    -0.65
    rone
    -0.64
    natureconservancy
    -0.61
    aires
    -0.61
    ILY
    -0.60
    JV
    -0.60
    POSITIVE LOGITS
    hand
    0.94
    rely
    0.90
     embark
    0.84
     proceeding
    0.84
     concluding
    0.83
     departing
    0.81
    empt
    0.80
     entering
    0.78
     retiring
    0.78
    noon
    0.78
    Activations Density 0.038%

    No Known Activations