INDEX

Explanations

names or terms related to a specific geographical location or event

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

aries

-1.04

ocene

-0.91

eller

-0.90

onica

-0.89

ocre

-0.87

alling

-0.85

erry

-0.84

ieval

-0.84

ation

-0.83

andowski

-0.83

POSITIVE LOGITS

 Creed

0.82

GROUND

0.69

 Skydragon

0.69

NECT

0.68

 Coliseum

0.67

 Bland

0.66

Â¯Â¯

0.63

 Indy

0.62

Aus

0.62

 Arrow

0.62

Activations Density 0.056%

names or terms related to a specific geographical location or event

No Comments

No Known Activations