INDEX

Explanations

the beginning of a new segment in the text

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

 -------

-0.73

hibernate

-0.73

ʹ

-0.70

ンダー

-0.70

hwnd

-0.69

Eugen

-0.68

 Miche

-0.68

;"></

-0.68

idste

-0.68

<<<<<<<<

-0.67

POSITIVE LOGITS

…

1.02

...

0.86

[…]

0.86

 متعلقه

0.84

 Kowalski

0.82

 macrophages

0.81

makeConstraints

0.79

onnaissance

0.78

 Lazarus

0.78

 Telex

0.78

Activations Density 0.211%

the beginning of a new segment in the text

No Comments

No Known Activations