INDEX

Explanations

numerical calculations and values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

 Pingback

-0.81

 Meiji

-0.81

 Mete

-0.81

 Kono

-0.78

 Martine

-0.76

 Stepan

-0.76

Życiorys

-0.76

Graeme

-0.74

WriteBarrier

-0.73

Jeanne

-0.72

POSITIVE LOGITS

 виправивши

0.72

олові

0.71

 فريبيس

0.61

 مرئيه

0.60

ittar

0.60

Ử

0.60

сылкі

0.59

litch

0.57

qid

0.57

Accessors

0.55

Activations Density 1.123%

numerical calculations and values

No Comments

No Known Activations