INDEX

Explanations

terms related to movies and films

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_fs6144-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

6,144

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

ilities

-0.90

²¾

-0.77

ords

-0.77

 Haitian

-0.73

odox

-0.69

tnc

-0.69

sembly

-0.68

otics

-0.66

functional

-0.65

anting

-0.65

POSITIVE LOGITS

 theater

1.11

goers

1.11

 theaters

1.08

 theatre

1.00

 movies

0.98

 theat

0.95

 trilogy

0.94

going

0.93

 sequels

0.92

 movie

0.91

Activations Density 0.251%

terms related to movies and films

No Comments

No Known Activations