INDEX

Explanations

references and links related to various categories or subjects

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

Not in Any Lists

No Comments

Negative Logits

 Infórmanos

-0.68

GIVEREF

-0.63

AlterField

-0.59

XmlAccessType

-0.58

bitField

-0.57

vdots

-0.56

NOPQRST

-0.55

]:

-0.55

"),

-0.54

databind

-0.53

POSITIVE LOGITS

Przeczytaj

0.64

IVEREF

0.63

 pleaſure

0.61

 Cæsar

0.60

 houſe

0.59

 skydd

0.57

 figliu

0.57

 détru

0.57

 ſeveral

0.57

 leſs

0.57

Activations Density 0.078%

references and links related to various categories or subjects

No Comments

No Known Activations