INDEX

Explanations

references to specific geographic locations or institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 AssemblyCulture

-0.89

parsedMessage

-0.76

 Houſe

-0.74

 purpoſe

-0.74

-------------</

-0.72

ngdoc

-0.71

 leaſt

-0.71

 EClass

-0.71

bootstrapcdn

-0.70

хьтан

-0.70

POSITIVE LOGITS

Fullscreen

0.48

was

0.48

 cited

0.48

 infamous

0.47

 citada

0.47

 recounted

0.46

 gigantes

0.46

 storici

0.46

Hist

0.44

 lunga

0.44

Activations Density 0.629%

references to specific geographic locations or institutions

No Comments

No Known Activations