INDEX

Explanations

terms related to inclination and leaning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

Parcelize

-0.65

 cser

-0.61

róż

-0.61

ruptedException

-0.60

뀜

-0.59

뀔

-0.58

assable

-0.58

boh

-0.58

 OMITBAD

-0.58

 lebens

-0.58

POSITIVE LOGITS

 leaning

1.61

 leans

1.40

 leaned

1.32

Lean

1.30

leaning

1.22

 lean

1.20

 Lean

1.15

 tilted

1.14

 tilting

1.13

 inclination

1.11

Activations Density 0.205%

terms related to inclination and leaning

No Comments

No Known Activations