INDEX

Explanations

references to figures and tables in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Efq

-0.87

 leaſt

-0.81

 itſelf

-0.79

 houſe

-0.77

principalColumn

-0.77

 depositphotos

-0.77

 themſelves

-0.76

 betweenstory

-0.75

 myſelf

-0.75

 ſta

-0.74

POSITIVE LOGITS

<eos>

0.54

허

0.53

ParallelGroup

0.51

 estimés

0.50

.,

0.49

hri

0.48

Примітки

0.47

SuppressMessage

0.47

Activations Density 1.605%

references to figures and tables in a document

No Comments

No Known Activations