INDEX

Explanations

phrases related to potential risks and effects involving actions or decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 مشين

-0.62

 بيها

-0.55

ⓧ

-0.53

qos

-0.52

 informée

-0.50

chequer

-0.49

OpenHelper

-0.48

AfterClass

-0.48

writeFieldEnd

-0.47



-0.47

POSITIVE LOGITS

 виправивши

0.77

 path

0.77

path

0.71

MLLoader

0.68

SPATH

0.67

 PATH

0.63

 Paths

0.63

 scope

0.61

PRNewswire

0.61

PATH

0.59

Activations Density 0.389%

phrases related to potential risks and effects involving actions or decisions

No Comments

No Known Activations