INDEX

Explanations

terms related to law enforcement and organizational roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Kjelder

-0.94

Билгалдахарш

-0.73

 Balkans

-0.72

RenderAtEndOf

-0.71

 <<<<<<<<<<<<<<

-0.71

uxxxx

-0.70

 presidencial

-0.69

 dépens

-0.69

Palmar

-0.69

 Bertie

-0.68

POSITIVE LOGITS

com

1.21

com

1.01

Com

0.77

Com

0.74

edu

0.66

 short

0.64

 General

0.59

pos

0.59

POS

0.57

comm

0.55

Activations Density 0.144%

terms related to law enforcement and organizational roles

No Comments

No Known Activations