INDEX

Explanations

specific numerical details or references within the text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ירות

-0.49

 variable

-0.49

greenrobot

-0.47

 δικ

-0.46

Solr

-0.45

!*\

-0.42

 ResponseEntity

-0.42

rè

-0.42

hoedd

-0.42

*",

-0.40

POSITIVE LOGITS

 препратки

0.74

 iconLine

0.69

 tartalomajánló

0.67

thâu

0.66

انيف

0.64

 SDLK

0.63

تقاوى

0.61

 ModelExpression

0.60

 ddelweddau

0.60

Anyways

0.60

Activations Density 0.175%

specific numerical details or references within the text

No Comments

No Known Activations