INDEX

Explanations

references to specific locations and organizations, particularly related to Columbia

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Alias

-0.60

cerea

-0.59

zap

-0.58

 Norris

-0.57

 alias

-0.53

 Flur

-0.52

xbe

-0.52

IH

-0.51

mathsf

-0.51

 Alison

-0.51

POSITIVE LOGITS

.*")]

1.06

 Stones

0.96

 Assisi

0.93

tvguidetime

0.90

LLocation

0.90

 odkazy

0.89

 Cryst

0.89

 Refle

0.89

__":

0.87

ⓧ

0.87

Activations Density 0.903%

references to specific locations and organizations, particularly related to Columbia

No Comments

No Known Activations