INDEX

Explanations

terms related to scientific components and processes

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

Kag

-0.98

gg

-0.98

ggg

-0.96

EndTag

-0.94

gag

-0.94

TAG

-0.93

 Vogt

-0.92

Wag

-0.92

 Margo

-0.92

SAG

-0.92

POSITIVE LOGITS

*__

0.76

 XCTest

0.76

__*/

0.75

PerformLayout

0.71

epresidente

0.69

]='\

0.69

Schön

0.66

Converse

0.65

makeConstraints

0.64

 Shee

0.63

Activations Density 1.415%

terms related to scientific components and processes

No Comments

No Known Activations