© 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. 11-RES-JB
    11. 3724
    Prev
    Next
    INDEX
    Explanations

    phrases related to difficult situations or challenges

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "struggle" and related expressions indicating difficulty or hardship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    """
    -0.70
    hemy
    -0.69
    acted
    -0.67
    Fax
    -0.66
     Wicked
    -0.66
    AAA
    -0.65
     Preferred
    -0.62
     Newspaper
    -0.61
     Means
    -0.60
    CI
    -0.60
    POSITIVE LOGITS
     cope
    1.28
     reconcile
    1.18
     survive
    1.17
     navigate
    1.15
     conceive
    1.10
     find
    1.09
     regain
    1.03
     fend
    1.03
     decipher
    1.01
     maintain
    1.00
    Activations Density 0.178%

    No Known Activations