INDEX

Explanations

references to individuals' names and titles, particularly in a biographical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 itſelf

-0.93

Efq

-0.88

 Anſ

-0.87

ReusableCell

-0.84

 doubtnut

-0.82

 iſt

-0.81

 Majefty

-0.80

 faſt

-0.80

 ―――――

-0.78

 myſelf

-0.78

POSITIVE LOGITS

THISDAY

0.58

 Honourable

0.57

 organised

0.55

lagos

0.54

 Organisations

0.53

 characterised

0.52

 popularly

0.50

 Programmes

0.50

 organisations

0.50

ab

0.49

Activations Density 0.333%

references to individuals' names and titles, particularly in a biographical context

No Comments

No Known Activations