INDEX

Explanations

instances of the word "started" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 Honeywell

-0.88

WX

-0.86

 contextLoads

-0.83

 Cowper

-0.83

quelize

-0.82

 Coliseum

-0.81

 itemprop

-0.80

Errorf

-0.79

Piz

-0.79

POSITIVE LOGITS

 start

1.61

 starts

1.53

 started

1.49

 START

1.47

START

1.46

 Start

1.44

 Starts

1.42

starts

1.39

Start

1.36

started

1.33

Activations Density 0.087%

instances of the word "started" and its variations

No Comments

No Known Activations