INDEX

Explanations

phrases indicating intentions or plans involving action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

存于互联网档案馆

-0.98

ThroughAttribute

-0.97

Бахар

-0.89

 Nestor

-0.88

 zelve

-0.88

\{\\

-0.86

 lenker

-0.86

verwijspagina

-0.83

 tasche

-0.82

 InputDecoration

-0.80

POSITIVE LOGITS

 Gonna

1.20

 gonna

1.20

Gonna

1.18

 GONNA

1.12

gonna

1.04

 will

0.87

 wanna

0.86

be

0.86

 want

0.85

 gotta

0.83

Activations Density 0.082%

phrases indicating intentions or plans involving action

No Comments

No Known Activations