INDEX

Explanations

references to personal interests and passions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

KURZBESCHREIBUNG

-0.77

IsContent

-0.76

期刊论文

-0.72

 Roskov

-0.72

 ujednoznacz

-0.70

GEBURTS

-0.69

 aveug

-0.68

 CreateTagHelper

-0.68

 dimaksud

-0.68

CloseOperation

-0.66

POSITIVE LOGITS

 animals

0.64

 anything

0.61

 adventure

0.61

Anything

0.54

 tinkering

0.54

 cleanliness

0.54

 sweets

0.53

 music

0.53

 nature

0.53

 outdoors

0.52

Activations Density 0.235%

references to personal interests and passions

No Comments

No Known Activations