INDEX

Explanations

terms related to assessment and evaluation outcomes

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

followed by adverbs or prepositions

np_acts-logits-general · gemini-2.0-flash

technical and financial reporting

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

-0.34

-0.32

-0.31

 sense

-0.30

-0.29

[toxicity=0]

-0.28

 instead

-0.28

Viki

-0.28

POSITIVE LOGITS

ंदीखरीदारी

1.04

Diwedd

0.85

tonode

0.83

IsMutable

0.80

MethodManager

0.80

ValueStyle

0.79

tagHelperRunner

0.79

 EconPapers

0.79

#+#

0.78

httphttps

0.78

Activations Density 1.756%

terms related to assessment and evaluation outcomes

followed by adverbs or prepositions

technical and financial reporting

No Known Activations