INDEX

Explanations

names related to a specific superhero, Spider-Man

oai_token-act-pair · gpt-3.5-turbo

mentions of comic book characters, particularly from the X-Men and Spider-Man franchises

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

housing

-0.72

embed

-0.69

imentary

-0.69

sett

-0.68

resh

-0.66

 administ

-0.66

grain

-0.65

rup

-0.64

gran

-0.63

 mids

-0.63

POSITIVE LOGITS

 Apocalypse

0.91

âĦ¢:

0.87

 Origins

0.83

 Adventures

0.79

 Legends

0.77

 Investigations

0.76

 Trilogy

0.76

 Unleashed

0.75

 trilogy

0.75

 villains

0.75

Activations Density 0.047%

names related to a specific superhero, Spider-Man

mentions of comic book characters, particularly from the X-Men and Spider-Man franchises

No Comments

No Known Activations