INDEX

Explanations

occurrences of words starting with the letter 'w'

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

MigrationBuilder

-0.67

ReusableCell

-0.55

дера

-0.53

HomeAsUpEnabled

-0.53

 Daya

-0.52

定

-0.52

WriteLiteral

-0.52

重

-0.51

úmeros

-0.51

TER

-0.50

POSITIVE LOGITS

Personendaten

0.93

0.86

GraphicsUnit

0.86

Geplaatst

0.84

 raiſ

0.80

DockStyle

0.80

 myſelf

0.79

 againſt

0.79

 Monfieur

0.78

 whoſe

0.77

Activations Density 0.072%

occurrences of words starting with the letter 'w'

No Comments

No Known Activations