INDEX

Explanations

mentions of conspiracy-related terms

oai_token-act-pair · gpt-3.5-turbo

references to conspiracy theories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ESV

-0.75

TD

-0.69

ijk

-0.69

Thom

-0.68

esa

-0.65

ICAN

-0.65

older

-0.65

erred

-0.64

 Assist

-0.64

flush

-0.63

POSITIVE LOGITS

 theorists

1.52

 theorist

1.51

 theories

1.45

 theory

1.22

 theor

1.07

eering

1.03

 hatched

0.99

 conspiracy

0.96

 conspir

0.91

 Theory

0.90

Activations Density 0.031%

mentions of conspiracy-related terms

references to conspiracy theories

No Comments

No Known Activations