INDEX

Explanations

phrases indicating temporal duration or frequency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

zehn

-0.61

یی

-0.53

囲

-0.49

oredCriteria

-0.48

es

-0.47

บัติ

-0.47

δί

-0.47

ๆ

-0.46

的

-0.46

outputFile

-0.46

POSITIVE LOGITS

 inception

1.05

 antiquity

0.86

 childhood

0.86

 then

0.81

 arriving

0.78

RuleContext

0.76

 então

0.75

 ExecuteAsync

0.74

 dasarnya

0.70

WebServlet

0.70

Activations Density 0.067%

phrases indicating temporal duration or frequency

No Comments

No Known Activations