INDEX

Explanations

names of authors and contributors in academic references

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

 ThemeData

-0.52

withIdentifier

-0.49

OGND

-0.49

 nobis

-0.46

BeginContext

-0.45

 ujednoznacz

-0.45

WithIdentifier

-0.45

 kaynağından

-0.43

 puissent

-0.43

 nominal

-0.42

POSITIVE LOGITS

onson

0.68

Tembelea

0.65

sson

0.64

saraba

0.62

AILABLE

0.61

essen

0.60

mson

0.59

inson

0.58

ides

0.58

äischen

0.57

Activations Density 0.240%

names of authors and contributors in academic references

No Comments

No Known Activations