INDEX

Explanations

conditional phrases and terms related to safety and operational guidance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

createCanvas

-0.55

 sequenced

-0.52

ientôt

-0.51

 atardecer

-0.51

มาะ

-0.51

udesta

-0.48

 przecież

-0.47

locene

-0.47

 Precambrian

-0.47

ViewFeatures

-0.46

POSITIVE LOGITS

Erreferentziak

0.66

不必

0.60

+#+#

0.60

can

0.59

不用

0.59

bitField

0.58

 safely

0.58

就可以

0.56

"):

0.56

 mogen

0.55

Activations Density 0.352%

conditional phrases and terms related to safety and operational guidance

No Comments

No Known Activations