INDEX

Explanations

references to headwear and related accessories

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

AMAHA

-0.55

readystatechange

-0.52

äler

-0.51

cade

-0.50

zmir

-0.49

سخ

-0.49

väll

-0.48

FLU

-0.47

cơ

-0.47

 vPvB

-0.46

POSITIVE LOGITS

 heads

1.25

 hats

1.17

 head

1.17

 Heads

1.11

 Head

1.09

Heads

1.08

Head

1.05

 cabeça

1.05

 caps

1.05

 chapeau

1.03

Activations Density 0.369%

references to headwear and related accessories

No Comments

No Known Activations