INDEX

Explanations

references to educational institutions and academic publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

Hentet

-0.51

sony

-0.47



-0.46

 comerciais

-0.44

 brancas

-0.44

 arbete

-0.43

 aktiviteter

-0.42

 član

-0.42

 quelcon

-0.41

 blancas

-0.41

POSITIVE LOGITS

AnimationsModule

0.69

 للاسماء

0.68

المكان

0.68

曖昧さ回避

0.65

 Baillargeon

0.63

Eloquent

0.62

TextAppearance

0.61

modb

0.60

Література

0.59

Fordítás

0.59

Activations Density 0.369%

references to educational institutions and academic publications

No Comments

No Known Activations