INDEX

Explanations

words and phrases related to the `in` and `IN` terms, potentially indicating connections, pointers, or inclusions in a programming context

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

 ་་

-1.01

 ―――――

-0.96

BibitemShut

-0.93

 للمعارف

-0.84

 ――――――――

-0.84

 doubtnut

-0.82

 Theſe

-0.81

Berikut

-0.79

^(@)

-0.79

ARROLL

-0.77

POSITIVE LOGITS

IN

1.76

IN

1.76

in

1.62

In

1.57

In

1.50

getIn

1.19

 isIn

1.12

in

1.01

isIn

0.96

 Innes

0.94

Activations Density 0.244%

words and phrases related to the `in` and `IN` terms, potentially indicating connections, pointers, or inclusions in a programming context

No Comments

No Known Activations