© 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. 16954
    Prev
    Next
    INDEX
    Explanations

    phrases indicating excess or extremes

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing excess or being "too" much of something

    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
     Cast
    -0.68
     caster
    -0.67
     state
    -0.66
     service
    -0.64
     services
    -0.63
     supported
    -0.63
     pair
    -0.63
     consist
    -0.61
     professional
    -0.61
     spot
    -0.61
    POSITIVE LOGITS
    too
    4.05
    Too
    2.10
     Too
    1.79
     too
    1.54
    enough
    1.37
    yet
    1.20
    quite
    1.15
    wrong
    1.08
    very
    1.06
    andro
    1.02
    Activations Density 0.009%

    No Known Activations