INDEX

Explanations

questions that seek information or clarification about various topics

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

what questions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

ThroughAttribute

-0.65

 they

-0.59

 ujednoznacz

-0.58

she

-0.54

➋

-0.49

elemField

-0.48

ffions

-0.46

we

-0.46

he

-0.46

niająca

-0.45

POSITIVE LOGITS

 does

1.31

did

1.27

do

1.22

 Does

1.02

Did

0.99

Did

0.98

Does

0.98

did

0.92

does

0.91

Are

0.85

Activations Density 0.096%

questions that seek information or clarification about various topics

what questions

No Comments

No Known Activations