INDEX

Explanations

biological classification terms, specifically related to species, particularly within certain genera

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 CreateTagHelper

-0.48

≔

-0.48

omyelitis

-0.46

 terr

-0.46

parsedMessage

-0.46

 détaillé

-0.45

chalten

-0.44

 encant

-0.44

 dinosau

-0.43

bio

-0.43

POSITIVE LOGITS

UserScript

0.79

 EconPapers

0.79

 Савезне

0.75

 uLocal

0.74

تقاوى

0.67

 InputDecoration

0.67

قایناق‌لار

0.64

 BorderRadius

0.63

 Meksiku

0.61

########.

0.59

Activations Density 0.255%

biological classification terms, specifically related to species, particularly within certain genera

No Comments

No Known Activations