INDEX

Explanations

technical terms and concepts related to neuroscience and technology

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

soDeliveryDate

-0.79

yright

-0.78

ership

-0.77

enthal

-0.76

ohan

-0.74

ISION

-0.67

ashington

-0.67

owed

-0.67

ARP

-0.66

orah

-0.65

POSITIVE LOGITS

 substrate

0.86

mite

0.85

cules

0.82

 substr

0.74

wcsstore

0.71

mone

0.71

llular

0.71

arium

0.69

 containing

0.68

amines

0.67

Activations Density 0.019%

technical terms and concepts related to neuroscience and technology

No Comments

No Known Activations

technical terms and concepts related to neuroscience and technology

No Comments

No Known Activations