INDEX

Explanations

various forms of the term "offset."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

abestanden

-0.86

 baterai

-0.83

-0.82

 vapore

-0.79

 hvem

-0.79

Parcelize

-0.76

 "..\..\

-0.72

ActionCreators

-0.71

IsPostBack

-0.70

lihatkan

-0.69

POSITIVE LOGITS

 offset

2.30

 Offset

2.27

 offsets

2.14

offset

2.06

Offset

2.06

 OFFSET

1.86

OFFSET

1.75

offsets

1.60

Offsets

1.50

偏移

1.32

Activations Density 0.096%

various forms of the term "offset."

No Comments

No Known Activations