INDEX

Explanations

numerical values, particularly those that appear in calculations or mathematical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 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

 للمعارف

-0.57

PullParser

-0.56

mány

-0.55

downloader

-0.53

 Schul

-0.52

ooplankton

-0.52

 Dyck

-0.52

 Downey

-0.51

cipl

-0.50

KUR

-0.50

POSITIVE LOGITS

1.61

۶

0.90

６

0.87

৬

0.84

0.77

 sixth

0.75

 sechs

0.73

 Sixth

0.72

۶

0.69

 шести

0.68

Activations Density 0.606%

numerical values, particularly those that appear in calculations or mathematical contexts

No Comments

No Known Activations