INDEX

Explanations

references to consistency and agreement across statements or observations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

actus

-0.50

žd

-0.48

 externes

-0.47

 tasked

-0.45

 unsuccessfully

-0.44

 Norris

-0.44

Kevin

-0.44

getSource

-0.43

CaseSensitive

-0.43

デカ

-0.43

POSITIVE LOGITS

 conforms

0.99

 conform

0.91

 reflect

0.90

 accords

0.86

 reflects

0.86

 aligns

0.85

符合

0.83

reflect

0.83

webElementXpaths

0.81

 adapts

0.77

Activations Density 0.289%

references to consistency and agreement across statements or observations

No Comments

No Known Activations