INDEX

Explanations

references to disorder or confusion

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

Personendaten

-0.81

SequentialGroup

-0.78

 démocr

-0.76

 sauvages

-0.76

 lusso

-0.75

 seduta

-0.74

AntiForgeryToken

-0.71

 Tourisme

-0.69

 scolas

-0.69

 Expédié

-0.69

POSITIVE LOGITS

 mess

1.41

 Mess

1.14

mess

1.12

 MESS

1.09

 messes

1.07

Mess

0.98

MESS

0.88

getMessage

0.68

mes

0.67

 agenda

0.67

Activations Density 0.028%

references to disorder or confusion

No Comments

No Known Activations