INDEX

Explanations

movie or TV show titles

oai_token-act-pair · gpt-3.5-turbo

titles of films and series

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ruary

-0.71

 waivers

-0.65

 deleg

-0.64

 chem

-0.63

mos

-0.61

itionally

-0.61

TN

-0.60

 opponents

-0.60

ierrez

-0.59

 coupled

-0.59

POSITIVE LOGITS

 Awakens

1.05

 Trilogy

0.90

 Bride

0.82

 Incident

0.82

 Angels

0.80

 Brigade

0.80

 Saga

0.78

 Shed

0.78

 Below

0.77

 Album

0.77

Activations Density 0.181%

movie or TV show titles

titles of films and series

No Known Activations