INDEX

Explanations

mentions of the Associated Press (AP) or its abbreviation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ClientSize

-1.04

 gynhyrchwyd

-0.96

UnusedPrivate

-0.87

parsedMessage

-0.86

GeoNames

-0.83

 lenker

-0.83

AddTagHelper

-0.82

NewGuid

-0.82

ChildIndex

-0.80

gdx

-0.77

POSITIVE LOGITS

ap

2.07

AP

2.04

AP

1.98

Ap

1.95

ap

1.91

Ap

1.81

APM

1.21

APIS

1.08

Aps

1.07

apta

1.01

Activations Density 0.101%

mentions of the Associated Press (AP) or its abbreviation

No Comments

No Known Activations