INDEX

Explanations

occurrences of proper nouns, particularly names and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

aarrggbb

-0.53

 initComponents

-0.50

araman

-0.47

pañol

-0.46

 empress

-0.46

BeginInit

-0.45

Cursors

-0.44

 laude

-0.43

sqcup

-0.43

republik

-0.43

POSITIVE LOGITS

 Enquiries

0.73

Sadly

0.66

Enquiries

0.65

 jadx

0.64

 Sadly

0.64

 enquiries

0.63

 sadly

0.62

Mum

0.62

Mum

0.62

 predeceased

0.59

Activations Density 0.073%

occurrences of proper nouns, particularly names and titles

No Comments

No Known Activations