INDEX

Explanations

references to individuals and entities associated with literary achievements and awards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

ك

-0.77

findpost

-0.74

mola

-0.73

Dud

-0.70

diego

-0.69

splitlines

-0.68

 Cedar

-0.68

Cedar

-0.68

 Stewart

-0.68

juna

-0.66

POSITIVE LOGITS

 houſe

1.18

 Majefty

1.09

^(@)

1.09

Efq

1.07

 purpoſe

1.07



1.06

 fubject

1.04

CIF

0.94

 doubtnut

0.94

 Houſe

0.94

Activations Density 1.595%

references to individuals and entities associated with literary achievements and awards

No Comments

No Known Activations