INDEX

Explanations

words or numbers that are near each other in a political or sales context

oai_token-act-pair · gemini-2.0-flash

decisive victory

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 informée

-0.67

fromnode

-0.59

 HasFactory

-0.56

 EconPapers

-0.54

yntaxException

-0.54

lgari

-0.53

protoimpl

-0.53

 CreateTagHelper

-0.53

 ErrIntOverflow

-0.53

TintMode

-0.52

POSITIVE LOGITS

 easily

1.02

 overwhelming

0.93

easily

0.92

 dominating

0.86

 blowout

0.85

 Easily

0.82

 dominant

0.81

 dominance

0.80

lop

0.77

 crushing

0.77

Activations Density 0.963%

words or numbers that are near each other in a political or sales context

decisive victory

No Comments

No Known Activations