INDEX

Explanations

technical jargon or programming-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 defaultstate

-0.91

 CreateTagHelper

-0.77

الحياه

-0.76

MLLoader

-0.76

protoimpl

-0.72

 EconPapers

-0.72

RectangleBorder

-0.69

InputBorder

-0.69

 createState

-0.67

 utafitiHapana

-0.67

POSITIVE LOGITS

<bos>

0.43

::_('

0.42

washingtonpost

0.41

[]:

0.40

ècie

0.39

wyt

0.38

owitz

0.38

ISODE

0.38

dbl

0.38

crombie

0.38

Activations Density 1.002%

technical jargon or programming-related terms

No Comments

No Known Activations