INDEX

Explanations

locations or places near a specific point

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

BILL

-0.84

alian

-0.74

ãĥīãĥ©

-0.72

Wire

-0.71

oeuv

-0.71

Percent

-0.71

Written

-0.70

etti

-0.70

ISM

-0.70

oleon

-0.67

POSITIVE LOGITS

shore

0.99

 campus

0.86

 midnight

0.82

 Bethlehem

0.81

sighted

0.79

 Interstate

0.76

 Naples

0.75

 Yellowstone

0.74

 Coff

0.73

 Yosemite

0.73

Activations Density 0.034%

locations or places near a specific point

No Comments

No Known Activations