INDEX

Explanations

instances of significant numerical or legal terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 noDo

-0.81

aarrggbb

-0.78

 Roskov

-0.73

Véxase

-0.73

 tartalomajánló

-0.70

RegressionTest

-0.65

EndInit

-0.64

 Administrativna

-0.64

 Савезне

-0.62

 <<<<<<<<<<<<<<

-0.61

POSITIVE LOGITS

AddTagHelper

0.64

ConstraintMaker

0.60

Portale

0.58

HasAnnotation

0.58

ecap

0.58

rinfo

0.55

AxisAlignment

0.52

%;

0.52

HomeAsUpEnabled

0.51

AndEndTag

0.51

Activations Density 0.489%

instances of significant numerical or legal terms

No Comments

No Known Activations