INDEX

Explanations

quantitative descriptors and percentages related to statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Efq

-0.78

 Theſe

-0.73

 EconPapers

-0.67

 ſhall

-0.67

 @"";

-0.65

 Jefus

-0.64

 löyty

-0.64

 Paglinawan

-0.63

 Majefty

-0.61

).__

-0.58

POSITIVE LOGITS

of

0.68

 مرئيه

0.63

 يتيمه

0.57

ldc

0.54

RegressionTest

0.53

Rptr

0.50

 Rptr

0.49

retch

0.47

0.46

0.45

Activations Density 0.301%

quantitative descriptors and percentages related to statistics

No Comments

No Known Activations