INDEX

Explanations

repeated phrases or patterns in text

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

醐

-0.67

{{$

-0.63

{{$

-0.60

gül

-0.59

 Bisch

-0.58

ად

-0.57

 point

-0.56

@@@@@@@@

-0.56

labelledby

-0.55

="{{$

-0.55

POSITIVE LOGITS

...

2.96

 ....

2.33

…

2.32

!...

2.13

...

2.11

 ..."

2.11

(...

2.09

 .....

2.08

,...

2.06

 ...)

2.06

Activations Density 0.136%

repeated phrases or patterns in text

No Comments

No Known Activations