INDEX

Explanations

instances of the word "reply."

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

مصادر

-0.84

LikeLike

-0.83

AndEndTag

-0.80

{!!

-0.79

ificantly

-0.74

>(&

-0.73

~*~

-0.73

 Moseley

-0.72

AxisAlignment

-0.72

inst

-0.70

POSITIVE LOGITS

 reply

1.76

 replies

1.72

reply

1.59

replies

1.47

 Reply

1.44

 replied

1.42

 replying

1.40

Replies

1.37

 REPLY

1.36

 Replies

1.22

Activations Density 0.136%

instances of the word "reply."

No Comments

No Known Activations