INDEX

Explanations

phrases indicating acknowledgment or agreement

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

таратура

-0.65

sidemargin

-0.61

shmi

-0.61

󠁢

-0.60

 henvisninger

-0.60

enoord

-0.58

 старости

-0.57

ondissement

-0.57

Unemployment

-0.57

Cubit

-0.57

POSITIVE LOGITS

Okay

1.10

Alright

1.09

 Okay

1.07

 Alright

1.02

OKAY

1.01

okay

0.95

Okey

0.93

Ok

0.89

alright

0.88

 okay

0.87

Activations Density 0.201%

phrases indicating acknowledgment or agreement

No Comments

No Known Activations