INDEX

Explanations

references to the movie franchise "Alien," including specific movie titles, characters, and the director

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

ients

-0.84

legate

-0.79

sub

-0.79

lees

-0.76

tons

-0.75

itably

-0.74

relations

-0.73

theless

-0.73

rooms

-0.72

ource

-0.72

POSITIVE LOGITS

 Predator

1.00

 Creed

0.95

 Trilogy

0.93

 Ridley

0.93

 sequels

0.90

 Resurrection

0.88

buster

0.86

 Recall

0.85

 trilogy

0.83

 Runner

0.83

Activations Density 0.055%

references to the movie franchise "Alien," including specific movie titles, characters, and the director

No Comments

No Known Activations