INDEX

Explanations

references to information or content that is presented below in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

AndEndTag

-0.95

Vidite

-0.90

########.

-0.87

]='\

-0.87

IsContent

-0.86

IVEREF

-0.85

StoryboardSegue

-0.84

erunner

-0.82

#+#

-0.79

ConstraintMaker

-0.79

POSITIVE LOGITS

 below

1.15

 above

1.10

Below

0.97

 Below

0.96

below

0.92

above

0.91

 abaixo

0.89

 following

0.82

 BELOW

0.80

 acima

0.78

Activations Density 0.312%

references to information or content that is presented below in a document

No Comments

No Known Activations