INDEX

Explanations

references to complete articles or stories

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

full story, full review

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

 propOrder

-0.47

tonsoft

-0.47

 secas

-0.45

 ſta

-0.45

 faſt

-0.44

 enfans

-0.43

 vägen

-0.42

 becauſe

-0.42

 prêtres

-0.42

 cúp

-0.41

POSITIVE LOGITS

 full

0.96

 Full

0.95

Full

0.85

 FULL

0.75

full

0.75

<bos>

0.65

FULL

0.62

RegressionTest

0.54

 penuh

0.54

 peł

0.54

Activations Density 0.006%

references to complete articles or stories

full story, full review

No Comments

No Known Activations