INDEX

Explanations

imperative phrases or commands

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Efq

-0.79

InjectAttribute

-0.74

 Hampden

-0.73

 miglia

-0.73

 palvel

-0.71

ondissement

-0.68

maison

-0.64

TagMode

-0.63

 døde

-0.63

 servici

-0.63

POSITIVE LOGITS

Lets

0.94

 lets

0.94

 Lets

0.84

try

0.78

 start

0.72

reactstrap

0.72

see

0.70

let

0.68

vamos

0.66

Vamos

0.64

Activations Density 0.063%

imperative phrases or commands

No Comments

No Known Activations