INDEX

Explanations

numerical data presented in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

XtraReports

-0.55

 ISNI

-0.54

 JpaRepository

-0.51

protoimpl

-0.51

 pngtree

-0.50

 Shortcuts

-0.50

 Derivation

-0.49

 CreateTagHelper

-0.49

 aprobó

-0.49

greenrobot

-0.49

POSITIVE LOGITS

发表于

0.54

tinyos

0.52

 برانيه

0.51

 coeur

0.48

 يتيمه

0.48

dom

0.47

 religieuses

0.47

níků

0.47

تفصیلات

0.46

❦

0.46

Activations Density 0.189%

numerical data presented in scientific contexts

No Comments

No Known Activations