INDEX

Explanations

references to input and output parameters in code contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 HasFactory

-0.85

 Mejía

-0.81

 Forumite

-0.78

 Exactos

-0.78

 Charlemagne

-0.78

 виправивши

-0.77

 Achille

-0.77

 Athan

-0.76

 itſelf

-0.74

ImageContext

-0.73

POSITIVE LOGITS

Input

1.80

 Input

1.31

Output

1.14

INPUT

0.80

 输入

0.73

UserInput

0.68

 Output

0.67

 getInput

0.67

Inputs

0.64

InputLabel

0.62

Activations Density 0.077%

references to input and output parameters in code contexts

No Comments

No Known Activations