INDEX

Explanations

negative evaluations of experiences or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

Vidite

-0.40

AddTagHelper

-0.40

 intensi

-0.33

 الحره

-0.32

 verify

-0.32

 stä

-0.32

 intensifies

-0.31

 intensify

-0.31

vindo

-0.30

RTLI

-0.30

POSITIVE LOGITS

 poorly

0.75

 buruk

0.74

 horrible

0.67

 poor

0.67

 mediocre

0.66

 mediocrity

0.65

 dismal

0.64

 crappy

0.63

Poor

0.63

 schlechte

0.63

Activations Density 0.476%

negative evaluations of experiences or items

No Comments

No Known Activations