INDEX

Explanations

occurrences of the word "for"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 ་་

-1.54

 iſt

-1.53

 myſelf

-1.51

 itſelf

-1.48

 raiſ

-1.45

 ſind

-1.43

 purpoſe

-1.42

 doubtnut

-1.39

 ſeveral

-1.37

 pleaſure

-1.37

POSITIVE LOGITS

for

3.37

for

2.68

FOR

2.49

For

2.49

For

2.26

FOR

2.02

 für

1.92

 voor

1.85

 для

1.85

 untuk

1.77

Activations Density 0.543%

occurrences of the word "for"

No Comments

No Known Activations