INDEX

Explanations

specific names or terms related to various fields and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 esternos

-0.67

Viki

-0.56

setVerticalGroup

-0.55

ApiModel

-0.54

jména

-0.53

gium

-0.51

-0.50

measures

-0.50

iastical

-0.50

POSITIVE LOGITS

..\..\

0.60

 Lons

0.57

tshell

0.56

iaomi

0.55

 Signalez

0.55

солю

0.54

iffion

0.54

edding

0.53

,:),

0.53

verme

0.53

Activations Density 0.348%

specific names or terms related to various fields and concepts

No Comments

No Known Activations