INDEX

Explanations

instances of the letter 'l'

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

ite

-0.49

igar

-0.49

igate

-0.49

arynx

-0.49

leiter

-0.46

ir

-0.44

ArrowToggle

-0.44

ie

-0.44

 Arno

-0.43

iff

-0.43

POSITIVE LOGITS

Geplaatst

0.68

tvguidetime

0.66

LookAnd

0.65

 تضيفلها

0.64

RenderAtEndOf

0.64

resave

0.62

BeginInit

0.61

RegressionTest

0.60

WritableDatabase

0.60

MigrationBuilder

0.58

Activations Density 0.148%

instances of the letter 'l'

No Comments

No Known Activations