INDEX

Explanations

references to geographical locations and organizational terms related to structures and systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 aveug

-0.56

 scuole

-0.48

 vestiti

-0.47

väg

-0.46

ever

-0.46

 thermique

-0.46

 foncé

-0.45

 квар

-0.45

ში

-0.45

 uitvo

-0.45

POSITIVE LOGITS

 surface

0.91

 Surfaces

0.88

GEBURTSDATUM

0.88

 waarop

0.85

mybatisplus

0.83

surface

0.82

 surfaces

0.82

 Surface

0.81

########.

0.81

 SURFACE

0.80

Activations Density 0.758%

references to geographical locations and organizational terms related to structures and systems

No Comments

No Known Activations