INDEX

Explanations

statements made by individuals or quotes from sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

Mep

-0.60

 RSSSF

-0.53

 bure

-0.52

 Khrushchev

-0.51

 Allociné

-0.51

ISI

-0.50

 censi

-0.49

 censiti

-0.49

ImageContext

-0.49

 Ayur

-0.48

POSITIVE LOGITS

—

0.79

++]=

0.75

وقال

0.74

__(/*!

0.69

 former

0.67

]]:

0.66

BeginContext

0.66

]),

0.65

rof

0.64

Activations Density 0.046%

statements made by individuals or quotes from sources

No Comments

No Known Activations