INDEX

Explanations

proper nouns or specific names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 feeding

-0.56

feeding

-0.48

queryInterface

-0.47

 feed

-0.45

 source

-0.44

Dro

-0.43

uri

-0.42

 holding

-0.42

мони

-0.42

 TextAppearance

-0.41

POSITIVE LOGITS

canestro

0.74

Tikang

0.67

-------------</

0.66

ValueGeneration

0.62

OGND

0.61

 MonoBehaviour

0.61

NameInMap

0.60

 utafitiHapana

0.60

 ddelweddau

0.58

RTGC

0.58

Activations Density 0.425%

proper nouns or specific names

No Comments

No Known Activations