INDEX

Explanations

references to geographic locations and directions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

aarrggbb

-0.75

Efq

-0.71

 photolibrary

-0.70

thenReturn

-0.70

transQ

-0.70

 Ashford

-0.66

 itſelf

-0.65

NUMX

-0.65

 Anſ

-0.63

 født

-0.63

POSITIVE LOGITS

0.61

 North

0.55

north

0.54

 north

0.51

 onCancelled

0.48

řízen

0.48

ScopeManager

0.48

 NavController

0.48

ContentAsync

0.44

 vượt

0.43

Activations Density 0.225%

references to geographic locations and directions

No Comments

No Known Activations