INDEX

Explanations

references to health-related programs and their evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

orologio

-0.39

URLException

-0.37

astify

-0.36

槻

-0.35

occasione

-0.35

zeptember

-0.35

isand

-0.34

setTextSize

-0.34

 doInBackground

-0.34

 kaynağından

-0.33

POSITIVE LOGITS

HC

1.30

HH

1.21

HB

1.20

HF

1.17

HD

1.16

HA

1.15

hb

1.14

HM

1.14

HL

1.14

HC

1.13

Activations Density 2.002%

references to health-related programs and their evaluations

No Comments

No Known Activations