INDEX

Explanations

the word "specified" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 bVar

-0.68

җ

-0.65

 onAnimation

-0.59

fillType

-0.56

본

-0.56

webElementXpaths

-0.55

 typelib

-0.54

SpringBootTest

-0.54

 استنادى

-0.54

hood

-0.54

POSITIVE LOGITS

specified

1.16

 specified

1.13

 specify

1.02

 Specified

0.94

 Specify

0.89

 specifying

0.86

する

0.85

 specifies

0.84

指定

0.84

Specify

0.84

Activations Density 0.106%

the word "specified" in various contexts

No Comments

No Known Activations