INDEX

Explanations

numerical data, particularly dates and statistics

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 "..\..\..\

-1.08

 pleaſure

-0.93

}),

-0.92

Vidite

-0.92

 Majefty

-0.91

 "..\..\

-0.91

 Charlemagne

-0.90

HasForeignKey

-0.90

 متعلقه

-0.90

 bezeichneter

-0.89

POSITIVE LOGITS

Las

0.56

Mar

0.52

0.51

 Rosen

0.50

sor

0.49

 Sand

0.49

var

0.48

 Vargas

0.47

 Jack

0.46

Activations Density 0.193%

numerical data, particularly dates and statistics

No Comments

No Known Activations