INDEX

Explanations

occurrences of the word "using."

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

using (`(` or `directive`

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

ſelf

-0.42

 couteau

-0.42

PostInfinity

-0.41

 prochaines

-0.41

 vettore

-0.41

ConstraintMaker

-0.40

RTCF

-0.40

télé

-0.39

 fleuve

-0.38

 ProtoMessage

-0.38

POSITIVE LOGITS

using

1.23

USING

0.91

 using

0.86

 Using

0.84

Using

0.83

 USING

0.83

 usando

0.69

 CreateTagHelper

0.69

 menggunakan

0.66

 referenties

0.62

Activations Density 0.001%

occurrences of the word "using."

using (`(` or `directive`

No Comments

No Known Activations