INDEX

Explanations

words related to scientific understanding and insights into biological mechanisms

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

featureID

-0.70

parsedMessage

-0.68

IBOutlet

-0.66

EDEFAULT

-0.60

 surla

-0.59

delwed

-0.58

 IBOutlet

-0.58

 queſta

-0.55

GTCX

-0.52

quartile

-0.52

POSITIVE LOGITS

 processes

0.47

 origin

0.45

 origins

0.41

 mechanisms

0.40

läufe

0.38

 interactions

0.38

 skla

0.37

 human

0.36

 relationships

0.36

 origines

0.36

Activations Density 0.115%

words related to scientific understanding and insights into biological mechanisms

No Comments

No Known Activations