INDEX

Explanations

military and aerospace terminology

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

 propOrder

-0.74

addCriterion

-0.69

verwijspagina

-0.65

 actionMode

-0.59

principalTable

-0.58

DIPSETTING

-0.58

komna

-0.57

 CallOverrides

-0.56

ьаж

-0.55

 Meksiku

-0.55

POSITIVE LOGITS

 invented

0.68

一種

0.62

一种

0.61

 variant

0.59

 developed

0.58

 multipurpose

0.58

を採用

0.57

 adaptable

0.56

__))

0.55

這款

0.54

Activations Density 0.483%

military and aerospace terminology

No Comments

No Known Activations