© 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. 4-RES-JB
    11. 484
    Prev
    Next
    INDEX
    Explanations

    adverbs or adjectives ending in 'ly'

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and adverbs related to strength and support

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

    No Comments

    Negative Logits
    çīĪ
    -0.94
    illions
    -0.77
    inea
    -0.77
     Duchess
    -0.74
    £ı
    -0.72
    士
    -0.72
    adelphia
    -0.70
     Deaths
    -0.69
    ा
    -0.68
     Millions
    -0.67
    POSITIVE LOGITS
     (>
    0.74
     ambition
    0.72
     ambitions
    0.71
    gradient
    0.69
     defenses
    0.69
    ellow
    0.68
     directional
    0.68
     differentiation
    0.68
     tendency
    0.66
     characterization
    0.65
    Activations Density 0.297%

    No Known Activations