INDEX

Explanations

references to television episodes and their associated details

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



-0.86

 PhpStorm

-0.68

mappedBy

-0.64

 artistique

-0.61

 réaliste

-0.60

IRQn

-0.60

 dépens

-0.60

 abstrato

-0.58

 humaines

-0.58

 abstrait

-0.58

POSITIVE LOGITS

 remastered

1.10

 remaster

1.00

 reissue

0.89

 reprints

0.82

 retrospective

0.80

 restored

0.80

 collected

0.79

 reprint

0.78

 reprinted

0.75

 archive

0.75

Activations Density 0.300%

references to television episodes and their associated details

No Comments

No Known Activations