INDEX

Explanations

references to revisions, corrections, and updates in text

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

feira

-0.60

tvguidetime

-0.58

 SwitchCompat

-0.56

manjaro

-0.55

 MainAxisSize

-0.54

AxisSize

-0.54

AtIndexPath

-0.53

 bezeichneter

-0.51

anything

-0.50

 تانيه

-0.50

POSITIVE LOGITS

+#+#

0.84

 revised

0.76

setVerticalGroup

0.72

 refined

0.63

revised

0.62

Revised

0.61

VISED

0.59

 Revised

0.58

 revisions

0.57

refined

0.56

Activations Density 0.620%

references to revisions, corrections, and updates in text

No Comments

No Known Activations