INDEX

Explanations

terms and phrases associated with legal proceedings and arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

antMatchers

-0.59

mány

-0.49

TypedDataSet

-0.49

kegaard

-0.48

țul

-0.47

χω

-0.47

του

-0.46

zsche

-0.45

OpenHelper

-0.45

 doInBackground

-0.43

POSITIVE LOGITS

 orally

0.86

 pronunciation

0.79

 verbally

0.79

 oral

0.69

 Oral

0.67

 verbal

0.67

 interviews

0.66

 live

0.65

 Verbal

0.64

 orale

0.64

Activations Density 0.814%

terms and phrases associated with legal proceedings and arguments

No Comments

No Known Activations