INDEX

Explanations

phrases related to ongoing actions or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

autaire

-0.49

ritch

-0.49

 Grecs

-0.47

 Jayne

-0.46

ßerdem

-0.46

 glyph

-0.46

OOTDTY

-0.45

 parís

-0.45

actéristi

-0.45

艸

-0.45

POSITIVE LOGITS

 continue

1.80

 continued

1.71

continue

1.69

 continues

1.68

 continuing

1.65

 Continue

1.64

 Continues

1.57

Continue

1.49

continued

1.46

continues

1.46

Activations Density 0.098%

phrases related to ongoing actions or processes

No Comments

No Known Activations