INDEX

Explanations

references to specific locations and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

LookAnd

-0.69

 виправивши

-0.66

 وتسجيلات

-0.64

 BrowserModule

-0.64

ècie

-0.62

ffiche

-0.61

DeleteBehavior

-0.60

kuuta

-0.60

()]);

-0.60

ensitive

-0.59

POSITIVE LOGITS

 located

1.17

 situated

1.11

 nestled

0.90

located

0.88

 Located

0.85

 terletak

0.80

 Situated

0.79

 surrounded

0.79

Located

0.76

 situé

0.74

Activations Density 0.247%

references to specific locations and their characteristics

No Comments

No Known Activations