INDEX

Explanations

references to geographic locations and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 pleaſure

-0.71

 Monfieur

-0.67

 CHAPITRE

-0.66

 sois

-0.65

 houſe

-0.65

 kabát

-0.64

 myſelf

-0.60

 poffible

-0.59

 purpoſe

-0.59

 benne

-0.58

POSITIVE LOGITS

GEBURTSDATUM

0.76

 ujednoznacz

0.63

Autoritní

0.61

 CreateTagHelper

0.59

 AssemblyCulture

0.57

0.56

nie

0.55

pod

0.52

 autorytatywna

0.51

za

0.50

Activations Density 0.059%

references to geographic locations and names

No Comments

No Known Activations