INDEX

Explanations

specific letters or symbols often used in mathematical notations

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

帖最后由

-0.89

ImageContext

-0.87

MigrationBuilder

-0.77

RegressionTest

-0.77

principalTable

-0.75

+#+

-0.73

Personensuche

-0.72

 DialogResult

-0.71

تقاوى

-0.71

lllllllll

-0.70

POSITIVE LOGITS

0.81

 CreateTagHelper

0.63

0.59

 Schick

0.46

 Steck

0.44

<bos>

0.43

’

0.39

Binds

0.39

 long

0.36

Activations Density 0.035%

specific letters or symbols often used in mathematical notations

No Comments

No Known Activations