INDEX

Explanations

proper nouns related to the film industry

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names and titles associated with people and places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

è¦ļéĨĴ

-0.69

Īè

-0.66

 saturated

-0.62

ournal

-0.60

 stabil

-0.60

astern

-0.59

pac

-0.59

 polar

-0.58

 uncond

-0.58

ANA

-0.57

POSITIVE LOGITS

burg

0.67

Mob

0.67

rue

0.66

mania

0.65

Mania

0.65

vy

0.64

Wiki

0.64

 Kamp

0.63

 Brawl

0.63

esque

0.63

Activations Density 0.279%

proper nouns related to the film industry

proper nouns, particularly names and titles associated with people and places

No Comments

No Known Activations