INDEX

Explanations

punctuation and sentence structure markers

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tvguidetime

-0.85

 invokingState

-0.77

Hentet

-0.77

 Roskov

-0.74

 propOrder

-0.66

 EconPapers

-0.66

besondere

-0.64

AsUp

-0.64

Izvori

-0.64

中でも

-0.63

POSITIVE LOGITS

 Alternatively

0.97

Alternatively

0.90

 alternatively

0.84

 then

0.78

 Таким

0.74

 thus

0.73

Rinse

0.73

 Rinse

0.73

Eventually

0.73

这就是

0.70

Activations Density 0.562%

punctuation and sentence structure markers

No Comments

No Known Activations