INDEX

Explanations

references to personal experiences and identities

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

<bos>

-0.71

IsContent

-0.69

 TextInputType

-0.66

 arşivlendi

-0.64

 فريبيس

-0.62

 satunya

-0.60

󠁢

-0.60

InputBorder

-0.58

the

-0.57

POSITIVE LOGITS

 stratigraph

0.74

 Mijn

0.70

rungsseite

0.69

 meiner

0.69

tvguidetime

0.69

CppMethod

0.67

 meines

0.65

 vectra

0.64

 <>",

0.63

 nakalista

0.63

Activations Density 0.639%

references to personal experiences and identities

No Comments

No Known Activations