INDEX

Explanations

references to police authorities and related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

CLUDE

-0.58

 Wanderer

-0.56

čenje

-0.49

NOPQRST

-0.49

utang

-0.49

geometric

-0.49

Nutrient

-0.48

ęg

-0.47

Canonical

-0.47

antine

-0.47

POSITIVE LOGITS

 police

1.36

 Police

1.35

Police

1.28

police

1.23

 POLICE

1.20

 cops

1.14

 policemen

1.13

 policeman

1.11

 Policing

1.09

 Cops

1.04

Activations Density 0.404%

references to police authorities and related terminology

No Comments

No Known Activations