INDEX

Explanations

titles and names related to movies and TV shows

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

titles of popular film franchises and their sequels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_post

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

itone

-0.62

gian

-0.61

OTA

-0.60

alach

-0.56

alloc

-0.55

ishly

-0.55

onal

-0.53

 nasal

-0.52

ahon

-0.52

ng

-0.51

POSITIVE LOGITS

 Rivals

0.88

 Heist

0.80

 Edition

0.76

 Gleaming

0.74

 Awakens

0.71

 Extend

0.70

 Returns

0.69

 Shards

0.69

 Crusade

0.69

 Chapters

0.68

Activations Density 0.119%

titles and names related to movies and TV shows

titles of popular film franchises and their sequels

No Comments

No Known Activations