INDEX

Explanations

keywords and phrases related to visual illustrations and group references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 Paglinawan

-1.16

ArrowToggle

-0.89

SpringRunner

-0.77

 utafitiHapana

-0.74

 resourceCulture

-0.73

 jsPsych

-0.72

تقاوى

-0.72

ьаж

-0.69

 UserController

-0.69

enumii

-0.66

POSITIVE LOGITS

are

0.66

is

0.65

was

0.64

 अनुसार

0.62

[toxicity=0]

0.61

0.60

0.59

To

0.59

0.58

Activations Density 0.647%

keywords and phrases related to visual illustrations and group references

No Comments

No Known Activations