INDEX

Explanations

terms related to the context of illness or medical conditions, particularly those involving the flu and related biological processes

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

Nuke

-0.58

CLUYE

-0.54

förmig

-0.51

 découver

-0.50

 BoxDecoration

-0.49

 surface

-0.48

ULING

-0.48

UObject

-0.47

 avocado

-0.47

 DELLE

-0.46

POSITIVE LOGITS

fl

1.42

fla

1.25

Fla

1.21

Flu

1.20

fl

1.19

FL

1.19

Fl

1.19

FL

1.19

flu

1.18

FLO

1.17

Activations Density 3.431%

terms related to the context of illness or medical conditions, particularly those involving the flu and related biological processes

No Comments

No Known Activations