© 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. 6-RES-JB
    11. 19677
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize a comparison or hierarchy, with an emphasis on superlatives

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "even the most."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asus
    -0.77
    ————
    -0.76
    emp
    -0.75
    potion
    -0.73
    quit
    -0.72
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.70
    anism
    -0.69
    -+-+
    -0.68
    ¯¯¯¯
    -0.67
    oshenko
    -0.67
    POSITIVE LOGITS
     smallest
    1.18
     slightest
    1.17
     simplest
    0.98
     mundane
    0.96
     superf
    0.92
     youngest
    0.86
     casual
    0.85
     meager
    0.85
     modest
    0.84
     occasional
    0.83
    Activations Density 0.069%

    No Known Activations