INDEX

Explanations

specific scientific terms associated with medical contexts and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

cause

-0.35

Cause

-0.33

 cause

-0.33

onSearch

-0.33

pattern

-0.32

 النص

-0.31

Implicit

-0.30

 Cause

-0.30

Category

-0.30

Orsay

-0.30

POSITIVE LOGITS

ResponseWriter

0.66

UnusedPrivate

0.64

enderror

0.60

 snippetHide

0.56

RepeatedField

0.54

XmlAccessorType

0.51

unknownFields

0.51

 unknownFields

0.51

 ſind

0.50

esgue

0.50

Activations Density 0.172%

specific scientific terms associated with medical contexts and conditions

No Comments

No Known Activations