INDEX

Explanations

terms related to classifications and rankings of therapies

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 biograf

-0.53

${

-0.52

GETHER

-0.51

ۜ

-0.49

__(/*!

-0.47

Pel

-0.47

それでも

-0.46

ero

-0.46

${

-0.45

 entro

-0.45

POSITIVE LOGITS

 cauſe

0.79

abestanden

0.76

 surla

0.75

 faſt

0.67

 dieß

0.65

 ſche

0.64

enumi

0.63

RegressionTest

0.62

 Савезне

0.62

usercontent

0.61

Activations Density 0.713%

terms related to classifications and rankings of therapies

No Comments

No Known Activations