INDEX

Explanations

key points outlining limitations or shortcomings in studies or findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

########.

-0.79

expandindo

-0.79

LookAnd

-0.66

发表于

-0.66

FormTagHelper

-0.63

Koordinaten

-0.63

 autorytatywna

-0.62

 EdgeInsets

-0.62

 للمعارف

-0.62

 onCancelled

-0.61

POSITIVE LOGITS

cui

0.58

 which

0.57

 related

0.55

 important

0.50

 notable

0.49

 concerning

0.49

 regarding

0.49

 continuación

0.48

 relating

0.48

Activations Density 0.435%

key points outlining limitations or shortcomings in studies or findings

No Comments

No Known Activations