INDEX

Explanations

references to medical or scientific terms and processes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 chrétienne

-0.69

 Spartans

-0.68

✨:

-0.65

 propOrder

-0.65

 Flaming

-0.64

piring

-0.62

 verksamhet

-0.60

 verksam

-0.59

 Lacy

-0.58

Kariera

-0.58

POSITIVE LOGITS

aibo

0.74

ParallelGroup

0.67

 Nitrate

0.65

 Barry

0.65

Omega

0.65

IFA

0.64

initState

0.64

hawat

0.64

makeText

0.63

WireFormat

0.63

Activations Density 1.393%

references to medical or scientific terms and processes

No Comments

No Known Activations