INDEX

Explanations

concepts related to health-related evaluations and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 propOrder

-0.95

featureID

-0.89

webElementXpaths

-0.78

يكب

-0.72

PhysRevD

-0.70

typeorm

-0.68

StoryboardSegue

-0.68

 GenerationType

-0.67

AddTagHelper

-0.67

 мәкал

-0.66

POSITIVE LOGITS

 ubiquitous

0.87

ubi

0.75

 popular

0.75

 popularity

0.68

 universally

0.66

 staple

0.61

 everywhere

0.60

 beliebt

0.59

popular

0.59

 widely

0.59

Activations Density 0.452%

concepts related to health-related evaluations and classifications

No Comments

No Known Activations