INDEX

Explanations

actions and expressions related to testing limits and pushing boundaries

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hObject

-0.57

 '\\;'

-0.57

IZONTAL

-0.55

rawDesc

-0.54

 attach

-0.54

 torchvision

-0.54

 cytoplas

-0.53

Obrázky

-0.53

ControllerAdvice

-0.53

cellona

-0.52

POSITIVE LOGITS

 pushed

0.86

 challenged

0.86

Pushing

0.84

pushed

0.81

 pushes

0.79

 Pushing

0.79

challenged

0.78

 challenge

0.77

 pushing

0.76

 probed

0.74

Activations Density 0.240%

actions and expressions related to testing limits and pushing boundaries

No Comments

No Known Activations