INDEX

Explanations

references to a specific news agency

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

etiologically related scientific texts

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

awtextra

-0.73

webElementXpaths

-0.62

ValueStyle

-0.62

tagHelperRunner

-0.56

readFileSync

-0.56

Personensuche

-0.56

EndContext

-0.55

 recensement

-0.53

moveToFirst

-0.53

 consultato

-0.52

POSITIVE LOGITS

PTI

2.34

PTI

2.23

pti

0.71

PT

0.60

PT

0.56

 Reuters

0.50

PTR

0.49

 Narendra

0.47

AFP

0.46

PTA

0.45

Activations Density 0.001%

references to a specific news agency

etiologically related scientific texts

No Comments

No Known Activations

references to a specific news agency

etiologically related scientific texts

No Comments

No Known Activations