INDEX

Explanations

discussions surrounding political and social justice issues, particularly those involving rights and advocacy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 troubleshoot

-0.68

 виправивши

-0.67

تقاوى

-0.66

 kasarigan

-0.65

oredCriteria

-0.64

RectangleBorder

-0.64

 troubleshooting

-0.62

 الاطلاع

-0.60

มาะ

-0.60

ToDisplay

-0.58

POSITIVE LOGITS

 nuclear

0.64

tax

0.64

 abol

0.63

 abolish

0.61

 stricter

0.59

 universal

0.58

 increased

0.56

 allowing

0.55

 free

0.55

 compulsory

0.55

Activations Density 0.699%

discussions surrounding political and social justice issues, particularly those involving rights and advocacy

No Comments

No Known Activations