© 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. 460
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "All"

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of the word "All" in various contexts

    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
     rather
    -0.77
     approaches
    -0.63
     breathing
    -0.62
     squat
    -0.61
     dod
    -0.60
     warrant
    -0.60
     poorly
    -0.60
     near
    -0.60
     ways
    -0.59
     circa
    -0.59
    POSITIVE LOGITS
    All
    3.07
    all
    1.99
     All
    1.92
    ALL
    1.73
    Each
    1.71
    Everything
    1.68
    Any
    1.67
    None
    1.65
    Every
    1.55
     ALL
    1.52
    Activations Density 0.011%

    No Known Activations