INDEX

Explanations

references to news agencies and their reporting

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

news agency affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 InputDecoration

-0.88

AddTagHelper

-0.82

 EconPapers

-0.79

 виправивши

-0.77

expandindo

-0.76

thâu

-0.74

windowFixed

-0.73

ContentAlignment

-0.73

ollectionView

-0.72

 disambiguazione

-0.71

POSITIVE LOGITS

AFP

0.94

AFP

0.93

afp

0.65

afp

0.59

 feminina

0.33

UTERS

0.32

 Reuters

0.29

 dosp

0.29

<bos>

0.28

 Gaff

0.27

Activations Density 0.000%

references to news agencies and their reporting

news agency affiliations

No Comments

No Known Activations