INDEX

Explanations

references to mountains and related terrain features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

tanleria

-0.77

 InputDecoration

-0.76

homonymie

-0.68

ftagPool

-0.68

InputBorder

-0.63

 onCancelled

-0.61

tvguidetime

-0.61

 BoxDecoration

-0.60

 iconTwitter

-0.59

setVerticalGroup

-0.58

POSITIVE LOGITS

side

0.79

top

0.71

PreferredItem

0.62

 region

0.60

 dwellers

0.60

tops

0.59

 regions

0.58

TOP

0.56

 range

0.56

SIDE

0.55

Activations Density 0.082%

references to mountains and related terrain features

No Comments

No Known Activations