INDEX

Explanations

dates and numerical references

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

Dec followed by . or iding

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

 Vogel

-0.47

 Wiesen

-0.46

irit

-0.45

 Савезне

-0.45

 impe

-0.44

 איש

-0.42

Beauty

-0.42

beauty

-0.41

temun

-0.41

Wool

-0.41

POSITIVE LOGITS

Dec

2.20

Dec

2.13

dec

1.72

DEC

1.68

DEC

1.55

dec

1.52

 deca

1.27

 déc

1.20

 Decker

1.14

 deci

1.11

Activations Density 0.013%

dates and numerical references

Dec followed by . or iding

No Comments

No Known Activations

dates and numerical references

Dec followed by . or iding

No Comments

No Known Activations