INDEX

Explanations

proper nouns, particularly names of people, places, and relevant entities

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

PullParser

-0.85

ագրություններ

-0.82

GraphicsUnit

-0.82

bpp

-0.81

 Havel

-0.81

 Theſe

-0.80

 Olin

-0.79

 Keane

-0.78

Điện

-0.78

 iſt

-0.78

POSITIVE LOGITS

 Scotts

0.79

xca

0.78

 McCa

0.76

 Scott

0.72

 McCoy

0.71

 Kylie

0.71

getFrom

0.69

Tru

0.68

 Benav

0.68

RAP

0.68

Activations Density 2.962%

proper nouns, particularly names of people, places, and relevant entities

No Comments

No Known Activations