INDEX

Explanations

terms related to conspiracy theories

oai_token-act-pair · gpt-3.5-turbo

terms related 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 @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

rien

-0.79

Environment

-0.71

âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ

-0.67

zl

-0.66

Thom

-0.66

 Dion

-0.66

cknowled

-0.66

older

-0.65

isha

-0.64

inas

-0.64

POSITIVE LOGITS

 conspiracy

1.19

 theories

1.10

 theorists

1.08

 conspir

1.06

 theorist

1.01

 Conspiracy

0.86

 theory

0.84

 theor

0.84

 indictment

0.80

 hatched

0.79

Activations Density 0.011%

terms related to conspiracy theories

terms related to conspiracy theories

No Comments

No Known Activations