INDEX

Explanations

instances of the word "hack" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

czegó

-0.63

Yag

-0.59

 Borel

-0.59

 Nagel

-0.59

AccessorTable

-0.59

ThroughAttribute

-0.58

gebirge

-0.58

sequelize

-0.57

MessageOf

-0.57

 cdti

-0.56

POSITIVE LOGITS

sz

0.90

 Hack

0.90

hack

0.89

 hack

0.87

Hack

0.72

 HACK

0.70

 tricks

0.67

sz

0.65

Trick

0.64

Ox

0.63

Activations Density 0.113%

instances of the word "hack" in various contexts

No Comments

No Known Activations