INDEX

Explanations

terms related to variation and differences in a range of contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Hodgson

-0.60

-0.58

ch

-0.56

 đầu

-0.56

pl

-0.56

Mok

-0.55

Nuc

-0.54

ten

-0.54

mah

-0.54

க்க

-0.53

POSITIVE LOGITS

 Vary

1.32

 VIAF

1.31

 Vari

1.20

 Variation

1.17

 variation

1.16

Variations

1.16

 variations

1.15

Vary

1.15

 variances

1.12

 Varies

1.12

Activations Density 0.168%

terms related to variation and differences in a range of contexts

No Comments

No Known Activations