INDEX

Explanations

numerical data and associated values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

•test

No Comments

Negative Logits

Par

-0.53

di

-0.50

dat

-0.48

หน

-0.47

dig

-0.45

Sal

-0.45

 đầu

-0.45

Mar

-0.45

POSITIVE LOGITS

 myſelf

1.14

 itſelf

1.04

 Monfieur

0.96

 ſeveral

0.95

 leſs

0.94

ConstraintMaker

0.93

 Jefus

0.92

ſelf

0.91

 perſon

0.90

 pleaſure

0.89

Activations Density 1.348%

numerical data and associated values

No Comments

No Known Activations