INDEX

Explanations

significant nouns and phrases related to events or occurrences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Derfor

-0.74

 when

-0.70

 därför

-0.64

Ведь

-0.61

 therefore

-0.59

 everytime

-0.58

 derfor

-0.58

when

-0.58

 Deshalb

-0.57

 whenever

-0.57

POSITIVE LOGITS

Elsewhere

1.47

 Elsewhere

1.37

 Meanwhile

1.07

Meanwhile

1.02

Rounding

1.01

 elsewhere

1.00

 meanwhile

0.94

Also

0.92

 Also

0.89

 Among

0.88

Activations Density 0.134%

significant nouns and phrases related to events or occurrences

No Comments

No Known Activations