© 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. 9972
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a requirement or condition for something to happen or be successful, often starting with "to"

    oai_token-act-pair · gpt-3.5-turbo

    imperative statements or instructions directed at the reader

    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
     impunity
    -0.84
     innocence
    -0.66
    ulence
    -0.62
     hindsight
    -0.60
    cknowled
    -0.59
    Newsletter
    -0.59
     opin
    -0.57
     enjoyment
    -0.56
     Views
    -0.54
    cknow
    -0.54
    POSITIVE LOGITS
     need
    1.43
    need
    1.32
     needs
    1.26
     must
    1.23
     needed
    1.18
    needs
    1.16
     gotta
    1.13
    must
    1.10
     NEED
    1.04
     required
    0.98
    Activations Density 0.369%

    No Known Activations