INDEX

Explanations

instances of negation and uncertainty in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Seym

-0.77

 Vaugh

-0.69

enegger

-0.67

oppable

-0.66

avorite

-0.62

GBT

-0.62

 shenan

-0.61

 contrace

-0.60

 psychiat

-0.60

 arrang

-0.59

POSITIVE LOGITS

malink

0.63

 guiActiveUnfocused

0.61

join

0.60

 thumbnail

0.58

odes

0.58

enter

0.56

alyses

0.56

cius

0.55

ims

0.55

idity

0.54

Activations Density 0.242%

instances of negation and uncertainty in statements

No Comments

No Known Activations