INDEX

Explanations

references to the famous astrophysicist Neil deGrasse Tyson

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

ãĤ£

-0.84

BuyableInstoreAndOnline

-0.76

IENCE

-0.73

orically

-0.73

ances

-0.72

atable

-0.71

rative

-0.69

bitious

-0.69

liest

-0.68

joined

-0.68

POSITIVE LOGITS

 Carlson

0.76

ucker

0.72

 Fury

0.69

 Leilan

0.68

hawk

0.68

 Apost

0.67

 Hilton

0.66

illian

0.66

hops

0.66

hower

0.65

Activations Density 0.045%

references to the famous astrophysicist Neil deGrasse Tyson

No Comments

No Known Activations