INDEX

Explanations

conjunctions and linking words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

enumii

-0.77

Espèce

-0.70

enumi

-0.69

 NSCoder

-0.69

 fieldNum

-0.68

]")]

-0.67

gonic

-0.65

BeginContext

-0.65

SequentialGroup

-0.65

 bezeichneter

-0.64

POSITIVE LOGITS

和

3.18

和

2.44

和小

1.71

和大

1.69

和其他

1.56

与

1.55

跟

1.51

與

1.48

和他

1.48

和我

1.46

Activations Density 0.037%

conjunctions and linking words

No Comments

No Known Activations