INDEX

Explanations

references to API documentation and networking code elements

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

 gyhoeddwyd

-0.52

мони

-0.47

 Emer

-0.47

 optique

-0.45

tanleria

-0.44

ligente

-0.43

dAtA

-0.43

ctis

-0.43

 prinsip

-0.42

WSGI

-0.42

POSITIVE LOGITS

 OFDb

0.91

ViewImports

0.84

oa̍t

0.78

ViewFeatures

0.78

 otomatig

0.76

 BoxFit

0.74

[]:

0.73

IsContent

0.72

PositiveButton

0.72

InSection

0.71

Activations Density 0.498%

references to API documentation and networking code elements

No Comments

No Known Activations