INDEX

Explanations

academic terminology related to taxonomy and classification

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BagConstraints

-0.62

writerow

-0.57

IsContent

-0.57

 оригіналу

-0.56

Filmografie

-0.53

 kaynağından

-0.52

Sucesor

-0.51

omitempty

-0.51

 SPIE

-0.50

 AssemblyTitle

-0.49

POSITIVE LOGITS

发表于

0.61

 Meksiku

0.59

 Schlüssel

0.54

ёх

0.51

tinyos

0.51

 restring

0.50

 Touring

0.50

 Walkover

0.49

ifikasi

0.49

 restorations

0.49

Activations Density 0.795%

academic terminology related to taxonomy and classification

No Comments

No Known Activations