INDEX

Explanations

references to medical institutions and departments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ConstraintMaker

-1.12

 disambiguazione

-1.02

 Roskov

-0.99

 XNUMX

-0.95

NUMX

-0.88

istoitu

-0.84

期刊论文

-0.83

ніципалі

-0.82

rungsseite

-0.81

bootstrapcdn

-0.78

POSITIVE LOGITS

1.08

–

0.63

0.58

0.57

0.55

0.49

New

0.48

at

0.48

이

0.48

Activations Density 0.360%

references to medical institutions and departments

No Comments

No Known Activations