INDEX

Explanations

terms related to processes and their outcomes

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

 Theſe

-0.66

 وتسجيلات

-0.65

 quæ

-0.65

躇

-0.65

 ſche

-0.61

 Ανακτήθηκε

-0.61

évaluateur

-0.59

 Shaksp

-0.59

 Majefty

-0.59

AutoModerator

-0.59

POSITIVE LOGITS

0.70

że

0.58

verständlich

0.58

Diweddarwch

0.57

bcryptjs

0.56

UpInside

0.55

rval

0.54

yntaxException

0.53

følgelig

0.52

deepcopy

0.52

Activations Density 0.830%

terms related to processes and their outcomes

No Comments

No Known Activations