INDEX

Explanations

scientific terms and references related to quantitative analyses and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 EconPapers

-0.88

RenderAtEndOf

-0.81

 initComponents

-0.81

LookAnd

-0.77

 архивлан

-0.68

 propOrder

-0.66

ंदीखरीदारी

-0.64

+#+#

-0.63

RegressionTest

-0.63

UnusedPrivate

-0.61

POSITIVE LOGITS

ViewFeatures

0.73

 подо

0.46

waitKey

0.44

flink

0.44

 Best

0.44

 tarvit

0.44

Willkommen

0.44

 nửa

0.43

 frå

0.43

brido

0.42

Activations Density 0.380%

scientific terms and references related to quantitative analyses and statistics

No Comments

No Known Activations