INDEX

Explanations

phrases indicating obstructions or barriers

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

incinn

-0.83

ocally

-0.83

aughed

-0.82

iosyncr

-0.81

milo

-0.81

akespe

-0.75

ocry

-0.74

uesday

-0.69

irted

-0.69

olate

-0.68

POSITIVE LOGITS

 thereof

0.77

finding

0.76

liness

0.76

of

0.69

ward

0.66

 conversions

0.65

lihood

0.64

liest

0.63

.--

0.62

WARD

0.60

Activations Density 0.009%

phrases indicating obstructions or barriers

No Comments

No Known Activations