INDEX

Explanations

terms related to medical conditions and their assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

WithIOException

-0.83

 <=",

-0.72

-0.66

LookAnd

-0.61

Mes

-0.59

↵↵

-0.58

 Himo

-0.58

 >=",

-0.56

-0.55

POSITIVE LOGITS

 Monfieur

1.18

Efq

1.15

 itſelf

1.13

 ſeveral

1.12

 myſelf

1.10

 Jefus

1.08

 himſelf

1.03

 themſelves

1.03

 Anſ

1.01

 Theſe

1.00

Activations Density 3.908%

terms related to medical conditions and their assessments

No Comments

No Known Activations