INDEX

Explanations

terms related to medical conditions and their treatment

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 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

kegaard

-0.72

fty

-0.71

 Fayette

-0.71

aldehyde

-0.71

atitis

-0.71

)),

-0.70

umenical

-0.70

datable

-0.70

quatch

-0.70

ede

-0.69

POSITIVE LOGITS

SOR

1.09

ror

1.09

TOR

1.07

LOR

1.06

OR

1.05

Zor

1.04

mor

1.04

 Dorn

1.04

tor

1.03

or

1.01

Activations Density 0.478%

terms related to medical conditions and their treatment

No Comments

No Known Activations