INDEX

Explanations

signals of legal and medical terms related to safety and compliance context

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

 themſelves

-0.68

 myſelf

-0.61

 becauſe

-0.59

 Jefus

-0.58

 reaſon

-0.58

 Conſ

-0.57

 ſtate

-0.55

 fubject

-0.55

 fince

-0.54

 pleaſure

-0.54

POSITIVE LOGITS

 being

1.01

Билгалдахарш

0.82

being

0.79

 happening

0.78

 happen

0.74

 nahilalakip

0.74

 unknownFields

0.72

 occur

0.71

 sendo

0.71

ьаж

0.69

Activations Density 0.582%

signals of legal and medical terms related to safety and compliance context

No Comments

No Known Activations