INDEX

Explanations

references to unexpected outcomes or events

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

 NavController

-0.79

AfterClass

-0.63

hütte

-0.62

 CURLOPT

-0.61

Kat

-0.61

Kat

-0.60

brecht

-0.60

IMDG

-0.59

ArrowToggle

-0.58

 Klasse

-0.58

POSITIVE LOGITS

 Surprise

1.48

 surprise

1.40

 surprises

1.23

Surprise

1.20

surprise

1.15

 surprised

1.13

 surpris

1.09

 surprising

1.03

 overras

1.01

 Überras

1.00

Activations Density 0.074%

references to unexpected outcomes or events

No Comments

No Known Activations