INDEX

Explanations

references to low or mild levels of something, particularly in a medical or descriptive 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

Fordítás

-0.77

المناصب

-0.73

 defStyleAttr

-0.69

 againſt

-0.68

tagHelperRunner

-0.68

KURZBESCHREIBUNG

-0.65

 whoſe

-0.65

AndEndTag

-0.63

 pleaſure

-0.62

ConstraintMaker

-0.61

POSITIVE LOGITS

Low

2.60

Low

2.52

low

2.43

LOW

2.29

low

2.21

LOW

2.00

低

1.89

 lowest

1.83

 Lowest

1.61

 lows

1.58

Activations Density 0.121%

references to low or mild levels of something, particularly in a medical or descriptive context

No Comments

No Known Activations