INDEX

Explanations

references to rules or structures in language and code, particularly involving verb forms and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

tros

-0.50

 Erişim

-0.46

tó

-0.42

السكان

-0.42

win

-0.42

 turi

-0.40

ür

-0.40

jelent

-0.40

يكب

-0.39

POSITIVE LOGITS

<?

0.89

 itſelf

0.80

IntoConstraints

0.79

 виправивши

0.74

 يتيمه

0.74

WriteTagHelper

0.71

AndEndTag

0.70

 MainAxisSize

0.70

DotNetBar

0.70

 Monfieur

0.69

Activations Density 0.629%

references to rules or structures in language and code, particularly involving verb forms and conditions

No Comments

No Known Activations