INDEX

Explanations

references to specific programming terms and technical components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

<b>

-0.76

 Collins

-0.73

ruptcy

-0.73

 Kenney

-0.72

氓

-0.67

 Brawl

-0.67

 Rowe

-0.66

 Bedi

-0.66

 Malone

-0.66

formin

-0.65

POSITIVE LOGITS

 Guth

1.06

Билгалдахарш

1.01

 itſelf

0.92

--}}

0.91

 חיצוניים

0.90

 Pinocchio

0.88

 Theſe

0.88

Efq

0.86

 Demp

0.86

 Coch

0.84

Activations Density 0.575%

references to specific programming terms and technical components

No Comments

No Known Activations