INDEX

Explanations

phrases that direct readers to additional content or resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 bezeichneter

-1.12

parsedMessage

-0.99

ConstraintMaker

-0.98

Personendaten

-0.95

Personensuche

-0.93

StandardCharsets

-0.90

PerformLayout

-0.89

 ExecuteAsync

-0.89

bewerken

-0.88

CodedInputStream

-0.88

POSITIVE LOGITS

 Check

0.66

Check

0.65

check

0.64

Read

0.63

See

0.61

See

0.61

Watch

0.59

 check

0.58

 Read

0.57

 Find

0.57

Activations Density 0.225%

phrases that direct readers to additional content or resources

No Comments

No Known Activations