INDEX

Explanations

frequent occurrences of specific times or dates related to events

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

 resourceCulture

-0.83

numerusform

-0.75

Cześć

-0.74

دانشنامهٔ

-0.73

Witam

-0.72

#+#

-0.70

 سكانية

-0.68

Efq

-0.68

 Monfieur

-0.68

parsedMessage

-0.68

POSITIVE LOGITS

0.67

0.62

0.59

0.57

0.52

0.51

ització

0.48

 jonge

0.47

Activations Density 0.114%

frequent occurrences of specific times or dates related to events

No Comments

No Known Activations