INDEX

Explanations

locations or specific names mentioned in the text

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

ctor

-0.73

UNCH

-0.70

astern

-0.70

outhern

-0.68

ELF

-0.63

ICT

-0.62

assic

-0.62

ected

-0.61

chnology

-0.60

pport

-0.60

POSITIVE LOGITS

2.91

sburg

1.67

sie

1.51

sb

1.45

ski

1.41

sis

1.38

sf

1.36

sg

1.34

sburgh

1.34

sand

1.31

Activations Density 0.418%

locations or specific names mentioned in the text

No Comments

No Known Activations