INDEX

Explanations

terms indicating a relationship to previous references or comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 ujednoznacz

-0.91

GEBURTSDATUM

-0.88

 виправивши

-0.82

 nakalista

-0.73

 Wiktionnaire

-0.71

 initComponents

-0.69

Cyfarwyddwr

-0.68

 CreateTagHelper

-0.68

 colère

-0.67

 autorytatywna

-0.65

POSITIVE LOGITS

 thing

1.05

 amount

0.80

two

0.71

liest

0.70

 ones

0.67

iniest

0.66

 combination

0.64

angkutan

0.64

esomeness

0.63

 situation

0.63

Activations Density 0.772%

terms indicating a relationship to previous references or comparisons

No Comments

No Known Activations