INDEX

Explanations

positive sentiments and evaluations related to experiences or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

AndEndTag

-0.75

TagMode

-0.66



-0.61

__(/*!

-0.60

enumi

-0.56

 Protección

-0.56

✨:

-0.56

prepareStatement

-0.55

WebKit

-0.54

enumii

-0.54

POSITIVE LOGITS

Station

0.53

PerformLayout

0.49

*/].

0.47

úsqueda

0.46

 useful

0.46

Very

0.45

Hmmmm

0.45

 Useful

0.45

 asume

0.45

ровок

0.45

Activations Density 0.073%

positive sentiments and evaluations related to experiences or products

No Comments

No Known Activations