INDEX

Explanations

references to influence and impact, particularly in social and health contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 headlong

-0.44

styleType

-0.44

iums

-0.43

iado

-0.42

onedDateTime

-0.42

 péri

-0.41

 blushed

-0.40

ummies

-0.40

rigated

-0.40

rildi

-0.40

POSITIVE LOGITS

 impact

0.91

impact

0.81

 effects

0.81

 effect

0.80

effect

0.79

Impact

0.78

 impacts

0.77

 Impact

0.77

 influence

0.77

effects

0.76

Activations Density 0.577%

references to influence and impact, particularly in social and health contexts

No Comments

No Known Activations