INDEX

Explanations

components related to user interface prompts and user input handling in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 TextAppearance

-0.53

ніципа

-0.51

atigable

-0.47

)}_

-0.47

 QtCore

-0.47

woff

-0.47

smarty

-0.46

UrlResolution

-0.45

LOGY

-0.44

})_{

-0.44

POSITIVE LOGITS

 input

1.16

 choice

1.12

input

1.05

 prompt

1.01

prompt

0.98

Input

0.97

choice

0.96

Prompt

0.94

输入

0.94

 Input

0.94

Activations Density 0.189%

components related to user interface prompts and user input handling in programming

No Comments

No Known Activations