© 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. 0-RES-JB
    6. 11524
    Prev
    Next
    INDEX
    Explanations

    phrases related to enduring difficult situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "endure" and its variations, indicating a focus on enduring hardship or challenges

    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
     Parties
    -0.70
     Trick
    -0.68
     Marg
    -0.67
    opped
    -0.66
     Crypt
    -0.66
     Libertarian
    -0.65
     drawing
    -0.64
    strument
    -0.64
     Lobby
    -0.63
     collection
    -0.63
    POSITIVE LOGITS
     endure
    3.11
     endured
    2.73
     withstand
    2.30
     tolerate
    1.30
     lasts
    1.27
     lasted
    1.22
     survive
    1.15
     undergo
    1.15
     persists
    1.12
     persisted
    1.12
    Activations Density 0.020%

    No Known Activations