INDEX

Explanations

references to statistics or numerical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 pleaſure

-0.76

 nationaux

-0.63

 ſte

-0.62

 quæ

-0.62

 faſt

-0.61

 ſeveral

-0.57

 noires

-0.56

 femininas

-0.56

 houſe

-0.56

 priorité

-0.55

POSITIVE LOGITS

Personensuche

0.91

 nahilalakip

0.84

TagMode

0.80

 ModelExpression

0.75

Rhestr

0.74

ScopeManager

0.71

ьаж

0.69

OGND

0.69

IUrlHelper

0.68

 resourceCulture

0.68

Activations Density 0.101%

references to statistics or numerical data

No Comments

No Known Activations