INDEX

Explanations

specific academic or scientific terminology and their contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للاسماء

-0.94

SBATCH

-0.91

Datuak

-0.90

 مشين

-0.87

ValueStyle

-0.84

rungsseite

-0.83

 Савезне

-0.81

IntoConstraints

-0.78

 فريبيس

-0.78

 AssemblyTitle

-0.76

POSITIVE LOGITS

 VALUES

0.51

optarg

0.50

 transversal

0.49

 Coton

0.49

Urb

0.48

 Substances

0.48

argo

0.48

perger

0.47

para

0.47

gal

0.47

Activations Density 1.073%

specific academic or scientific terminology and their contexts

No Comments

No Known Activations