INDEX

Explanations

terms related to safety regulations and protective measures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 ComVisible

-0.83

GetEnumerator

-0.69

 pinulongan

-0.59

nloa

-0.55

 chaude

-0.54

SequentialGroup

-0.54

 sẻ

-0.53

 beginnetje

-0.52

 transfieras

-0.52

writeFieldEnd

-0.52

POSITIVE LOGITS

 anti

0.84

 antica

0.70

 antis

0.69

 Anti

0.68

Anti

0.67

 devices

0.66

 Devices

0.65

 reflective

0.64

 Faraday

0.64

 device

0.62

Activations Density 0.567%

terms related to safety regulations and protective measures

No Comments

No Known Activations