INDEX

Explanations

terms related to amplification and cancer treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

mazoo

-0.82

CRIM

-0.75

 Dura

-0.71

 tenues

-0.70

ruly

-0.70

?_

-0.68

hå

-0.68

 péri

-0.66

เคล

-0.66

 Winaray

-0.65

POSITIVE LOGITS

Amp

1.25

amp

1.15

 amps

1.09

 Hamp

1.05

Amp

1.04

amp

1.02

 amphi

1.00

 Amplifier

0.97

 Amphi

0.95

 ampoule

0.92

Activations Density 0.488%

terms related to amplification and cancer treatments

No Comments

No Known Activations