INDEX

Explanations

comparative statements emphasizing importance or improvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 خارجية

-0.48

}*/

-0.45

 sockaddr

-0.44

 artikkeli

-0.43

tisti

-0.41

chaften

-0.41

ISupport

-0.41

licação

-0.40

äste

-0.40

 Infórmanos

-0.39

POSITIVE LOGITS

 ever

1.45

 EVER

1.19

ever

1.15

EVER

1.08

Ever

1.04

 Ever

1.00

 jamais

0.97

 nunca

0.94

 never

0.89

 Nunca

0.85

Activations Density 0.100%

comparative statements emphasizing importance or improvement

No Comments

No Known Activations