© 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. 0-RES-JB
    11. 2691
    Prev
    Next
    INDEX
    Explanations

    words related to being active or in use

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "active" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    luck
    -0.79
    fell
    -0.77
     Pru
    -0.66
     Hume
    -0.66
     Bian
    -0.65
    ijk
    -0.65
    Tokens
    -0.64
    nah
    -0.63
     Cunningham
    -0.63
    TRUMP
    -0.62
    POSITIVE LOGITS
     active
    3.66
     inactive
    2.46
    active
    2.23
     Active
    2.20
    Active
    1.96
     actively
    1.51
    activity
    1.51
     activated
    1.47
     passive
    1.46
     dormant
    1.31
    Activations Density 0.010%

    No Known Activations