INDEX

Explanations

phrases related to associations and comparisons in research studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 متعلقه

-0.69

 EconPapers

-0.60

ellemző

-0.59

országban

-0.57

principalTable

-0.57

jelen

-0.56

 يتيمه

-0.56

IContainer

-0.55

Occ

-0.55

enoid

-0.54

POSITIVE LOGITS

 devenus

0.53

 suitability

0.52

mbito

0.51

ťaž

0.48

 digunakan

0.48

 blijkt

0.47

 dipakai

0.47

 dipilih

0.47

 Verf

0.47

 favored

0.46

Activations Density 1.110%

phrases related to associations and comparisons in research studies

No Comments

No Known Activations