INDEX

Explanations

concepts related to health, safety, and welfare implications in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 chofe

-0.70

 Inscrivez

-0.68

 purpoſe

-0.66

 houſe

-0.62

 myſelf

-0.61

 ſtate

-0.61

 reaſon

-0.59

 pleaſure

-0.59

 auffi

-0.57

 Monfieur

-0.57

POSITIVE LOGITS

 affected

1.43

 impacted

1.39

 influenced

1.21

 Affected

1.18

affected

1.17

 boosted

1.05

 enhanced

1.04

Affected

0.96

 stimulated

0.96

influenced

0.94

Activations Density 0.532%

concepts related to health, safety, and welfare implications in various contexts

No Comments

No Known Activations