INDEX

Explanations

comparisons and results related to tests and trials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

+:+

-0.83

 citoy

-0.71

RTEE

-0.71

WithIOException

-0.70

 ſur

-0.70

nodoc

-0.70

исленность

-0.68

SharedCtor

-0.68

 propOrder

-0.68

 purpoſe

-0.67

POSITIVE LOGITS

 '\\;'

0.68

 also

0.50

also

0.48

ALSO

0.48

 вообще

0.48

he

0.47

 أيضاً

0.46

ainya

0.45

 another

0.44

 Pingback

0.43

Activations Density 1.463%

comparisons and results related to tests and trials

No Comments

No Known Activations