INDEX

Explanations

terms related to fixed properties or parameters

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

 говоря

-0.55

getchar

-0.55

 jegy

-0.54

 volna

-0.54

bast

-0.52

 témo

-0.51

 úgy

-0.49

 hason

-0.48

ToProps

-0.48

 tovább

-0.47

POSITIVE LOGITS

 fixed

1.64

 Fixed

1.54

Fixed

1.46

 FIXED

1.45

fixed

1.45

FIXED

1.28

 fija

1.09

 finite

1.09

 fixe

1.07

 fijo

1.06

Activations Density 0.342%

terms related to fixed properties or parameters

No Comments

No Known Activations