INDEX

Explanations

terms associated with claims, allegations, and reports of misconduct or controversy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 חיצוניים

-0.67

DECREF

-0.60

 iconLine

-0.55

зулта

-0.54

 propOrder

-0.51

 algemene

-0.50

OGND

-0.50

 становника

-0.49

 frågor

-0.49

+#+#

-0.48

POSITIVE LOGITS

edly

0.95

 allegedly

0.86

 supposedly

0.85

 údaj

0.79

 angeb

0.76

 reportedly

0.76

 supuestamente

0.74

 claimed

0.70

 claims

0.69

supposed

0.68

Activations Density 0.245%

terms associated with claims, allegations, and reports of misconduct or controversy

No Comments

No Known Activations