INDEX

Explanations

locations and placements in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 referenties

-0.58

 Adop

-0.58

InitVars

-0.55

Debate

-0.54

 terk

-0.54

 faibles

-0.50

MessageOf

-0.48

)))),

-0.47

 ára

-0.47

äle

-0.47

POSITIVE LOGITS

 placed

0.84

 located

0.83

vic

0.78

 positioned

0.78

placed

0.72

 situated

0.70

Vic

0.69

 يتيمه

0.68

 ujednoznacz

0.66

 AppCompat

0.65

Activations Density 0.120%

locations and placements in a technical context

No Comments

No Known Activations