INDEX

Explanations

references to "pan" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Roskov

-1.22

ChildScrollView

-1.21

 doubtnut

-1.20

 ་་

-1.20

 ―――――

-1.19

 ſind

-1.16

 Jefus

-1.15

 myſelf

-1.12

Efq

-1.11

 Theſe

-1.10

POSITIVE LOGITS

Pan

1.15

pan

1.00

Pan

0.92

pan

0.91

fa

0.81

Fa

0.77

0.74

PAN

0.65

0.64

Activations Density 0.246%

references to "pan" in various contexts

No Comments

No Known Activations