INDEX

Explanations

references to identity verification, legal processes, and personal experiences related to bureaucratic interactions

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

TintMode

-0.52

SOF

-0.51

 kring

-0.49

ándote

-0.45

 кӀош

-0.44

Ár

-0.44

 endforeach

-0.43

ándolos

-0.42

accessor

-0.41

mities

-0.40

POSITIVE LOGITS

#+#

0.98

 الرياضيه

0.84

 utafitiHapana

0.82

 فريبيس

0.79

'{@

0.75

tableFuture

0.72

Hochspringen

0.71

GEBURTSDATUM

0.68

 <=",

0.64

 ModelRenderer

0.62

Activations Density 0.185%

references to identity verification, legal processes, and personal experiences related to bureaucratic interactions

No Comments

No Known Activations