© 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. 10214
    Prev
    Next
    INDEX
    Explanations

    phrases related to making an attempt or effort

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" in various contexts of trying or attempting actions

    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
     Returning
    -0.68
    furt
    -0.68
    ELD
    -0.66
     Removal
    -0.64
    ITIES
    -0.62
    """
    -0.61
     Annotations
    -0.61
    joy
    -0.61
     Continued
    -0.60
     Emerson
    -0.59
    POSITIVE LOGITS
     emulate
    1.30
     convince
    1.28
     imitate
    1.23
     recreate
    1.19
     persuade
    1.18
     replicate
    1.18
     figure
    1.09
     minimize
    1.07
     reconcile
    1.06
     solve
    1.05
    Activations Density 0.113%

    No Known Activations