INDEX

Explanations

numerical data and values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 production

-0.46

New

-0.45

all

-0.44

ss

-0.43

 Vincent

-0.43

 works

-0.42

 family

-0.42

 turn

-0.41

бин

-0.41

वा

-0.41

POSITIVE LOGITS

 MainAxisSize

1.01

tvguidetime

0.88

 سكانية

0.86

VersionUID

0.80

Sucesor

0.80

IsContent

0.77

+#+#

0.74

protoimpl

0.74

 Comprometido

0.73

PerformLayout

0.72

Activations Density 0.643%

numerical data and values

No Comments

No Known Activations