INDEX

Explanations

technical and scientific terms related to various fields, including biology, encryption, and legal terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Thron

-0.63

 bicchiere

-0.63

 tavolo

-0.61

 piatto

-0.60

 spørs

-0.60

 specchio

-0.60

lacian

-0.59

MOQ

-0.58

 Họ

-0.57

 slaap

-0.57

POSITIVE LOGITS

ENT

1.55

ent

1.50

ents

1.49

ento

1.36

enta

1.34

ence

1.33

ENTO

1.30

ENTS

1.30

ente

1.24

enc

1.23

Activations Density 2.656%

technical and scientific terms related to various fields, including biology, encryption, and legal terms

No Comments

No Known Activations