INDEX

Explanations

references to legs or related anatomical parts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Personensuche

-0.82

]--;

-0.66

 архивлан

-0.64

SMT

-0.61

rolid

-0.61

úgó

-0.61

 Holocene

-0.59

tâ

-0.58

HTT

-0.58

deleteUser

-0.58

POSITIVE LOGITS

leg

2.27

Leg

2.00

Leg

1.87

leg

1.84

LEG

1.55

 legs

1.48

LEG

1.32

legs

1.25

Legs

1.23

 Legs

1.22

Activations Density 0.035%

references to legs or related anatomical parts

No Comments

No Known Activations