INDEX

Explanations

terms related to medical or social conditions, particularly those involving disparity or categorization

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

URLException

-0.71

picasso

-0.70

 препратки

-0.69

ngdoc

-0.69

 previa

-0.68

bhan

-0.67

 cáo

-0.67

mientos

-0.66

Panamoan

-0.66

allclose

-0.63

POSITIVE LOGITS

PhysRevD

1.13

 Dink

0.92

DPR

0.90

DSS

0.89

DCA

0.87

DTS

0.86

getD

0.85

 Dons

0.85

Dv

0.85

Dn

0.85

Activations Density 1.353%

terms related to medical or social conditions, particularly those involving disparity or categorization

No Comments

No Known Activations