INDEX

Explanations

connections and relationships within directed graphs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.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

TagMode

-0.84

 propOrder

-0.69

WebServlet

-0.68

=$?

-0.68

IntoConstraints

-0.59

 Савезне

-0.57

 ujednoznacz

-0.56



-0.54

 Decided

-0.53

 الحره

-0.53

POSITIVE LOGITS

is

0.68

 leksikon

0.51

 cannot

0.50

 belongs

0.50

 appartient

0.50

 inwoners

0.49

 possède

0.49

unknownFields

0.49

 contains

0.48

 must

0.48

Activations Density 1.769%

connections and relationships within directed graphs

No Comments

No Known Activations