INDEX

Explanations

the word "spoilers" in various contexts

oai_token-act-pair · gpt-3.5-turbo

phrases related to spoilers in content

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

ndra

-0.76

rums

-0.73

urat

-0.71

HCR

-0.70

amina

-0.69

kt

-0.68

leanor

-0.67

ŃĶ

-0.67

llan

-0.66

rique

-0.66

POSITIVE LOGITS

 spoilers

1.09

 spoiler

1.07

oiler

1.03

OIL

0.95

 spoil

0.89

spo

0.88

 Spoiler

0.74

ervative

0.73

icious

0.68

":""},{"

0.68

Activations Density 0.039%

the word "spoilers" in various contexts

phrases related to spoilers in content

No Comments

No Known Activations