INDEX

Explanations

references to expressions of agreement or acknowledgment

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

 itſelf

-0.86

 myſelf

-0.83

ſelf

-0.80

 contextLoads

-0.80

 themſelves

-0.74

 himſelf

-0.74

ſelves

-0.70

 />";

-0.65

neſs

-0.64

 Tapatalk

-0.63

POSITIVE LOGITS

ResumeLayout

0.60

TagHelpers

0.53

 EconPapers

0.52

 cool

0.52

்க்க

0.52

Kod

0.52

Ols

0.52

tah

0.51

 Nadel

0.51

you

0.51

Activations Density 0.110%

references to expressions of agreement or acknowledgment

No Comments

No Known Activations