INDEX

Explanations

terms related to food and eating descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CommonModule

-0.81

skosten

-0.81

 BoxFit

-0.79

nitus

-0.74

躇

-0.73

 MenuView

-0.73

scriptcase

-0.71

skraft

-0.71

السكان

-0.70

swick

-0.69

POSITIVE LOGITS

er

1.29

ed

0.89

ized

0.87

ER

0.83

ه

0.80

ization

0.79

ised

0.79

rrrrrrrr

0.78

theless

0.77

RRRR

0.75

Activations Density 0.776%

terms related to food and eating descriptions

No Comments

No Known Activations