INDEX

Explanations

mentions of significant life events or experiences related to medical or professional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 BorderSide

-0.72

PhysRevD

-0.59

GEBURTSDATUM

-0.57

NUMX

-0.57

Pranala

-0.55

"])

-0.54

 nouveautés

-0.53

")"

-0.53

pannt

-0.52

 religieuses

-0.51

POSITIVE LOGITS

たびに

0.69

0.67

出版年

0.65

 succes

0.62

 periods

0.62

 times

0.61

 successive

0.61

 seasons

0.60

 past

0.59

 eras

0.57

Activations Density 0.422%

mentions of significant life events or experiences related to medical or professional contexts

No Comments

No Known Activations