INDEX

Explanations

quantitative data and statistics related to scores, points, and measurements in various contexts

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

RetentionPolicy

-0.72

webElementXpaths

-0.70

WriteTagHelper

-0.69

 мәкал

-0.61

 CGRectMake

-0.61

principalTable

-0.60

씩

-0.60

ArgsConstructor

-0.60

 linkovi

-0.58

oneofs

-0.58

POSITIVE LOGITS

 overall

0.62

overall

0.62

 total

0.59

Overall

0.58

 Overall

0.57

gesamt

0.57

whole

0.56

 entire

0.56

Whole

0.56

 whole

0.56

Activations Density 0.665%

quantitative data and statistics related to scores, points, and measurements in various contexts

No Comments

No Known Activations