INDEX

Explanations

contextual references to configuration settings and options in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

webElement

-0.63

IVEREF

-0.54

зулта

-0.50

 resourceCulture

-0.49

-0.44

up

-0.43

AutoScaleMode

-0.43

veratrol

-0.42

evos

-0.41

SerializedSize

-0.41

POSITIVE LOGITS

ſelves

0.85

ſelf

0.84

 FetchType

0.76

 ་་

0.76

Efq

0.75

 ſtate

0.74

licet

0.74

quelize

0.74

 itſelf

0.73

 Conſ

0.71

Activations Density 0.177%

contextual references to configuration settings and options in programming

No Comments

No Known Activations