INDEX

Explanations

terms related to medical conditions and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

LookAnd

-0.94

BeginContext

-0.74

DockStyle

-0.73

XMLSchema

-0.72

DebuggerNonUser

-0.72

󠁿

-0.68

__*/

-0.68

AndEndTag

-0.66

 typelib

-0.64

 Normdatei

-0.64

POSITIVE LOGITS

ésultat

0.64

 gynhyrchwyd

0.60

Ӕ

0.57

 विश्वसनीयता

0.56

epar

0.54

 autentic

0.51

Rè

0.47

principalTable

0.46

trise

0.46

الدراسه

0.45

Activations Density 0.813%

terms related to medical conditions and their implications

No Comments

No Known Activations