INDEX

Explanations

terms related to immune response and cytokine signaling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

GIVEREF

-0.39

CloseOperation

-0.35

 ajudá

-0.35

 adota

-0.33

 menggel

-0.33

 ModelExpression

-0.33

Còn

-0.32

 financeira

-0.32

IUrlHelper

-0.31

 nucleus

-0.31

POSITIVE LOGITS

tokine

0.81

 cytokines

0.76

 cytokine

0.75

PRNewswire

0.63



0.61

leukin

0.61

 propOrder

0.56

iotensin

0.53

WebElementEntity

0.52

RegressionTest

0.52

Activations Density 2.061%

terms related to immune response and cytokine signaling

No Comments

No Known Activations