INDEX

Explanations

references to individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

BagLayout

-0.90

Idy

-0.86

 doubtnut

-0.85

hysema

-0.82

)».

-0.80

 plagioclase

-0.79

 Harald

-0.79

 Nare

-0.79

ReadAll

-0.79

 purging

-0.78

POSITIVE LOGITS

 Persons

1.49

 Person

1.48

 PERSON

1.46

 person

1.45

Persons

1.41

 persons

1.36

person

1.35

 PERSONS

1.34

Person

1.31

persons

1.29

Activations Density 0.031%

references to individuals or groups

No Comments

No Known Activations