INDEX

Explanations

terms related to horse racing and racing-related activities

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

 Estudios

-0.57

Einzelnachweise

-0.55

 Estudio

-0.53

 supérieurs

-0.53

parsedMessage

-0.49

 חיצוניים

-0.47

 tantôt

-0.47

UnknownFields

-0.47

Estudio

-0.47

 ananas

-0.46

POSITIVE LOGITS

 races

1.10

 racing

1.08

 race

1.06

 Racing

1.01

 horses

0.94

Racing

0.93

 jockey

0.92

 raced

0.92

racing

0.90

 horse

0.87

Activations Density 0.013%

terms related to horse racing and racing-related activities

No Comments

No Known Activations