INDEX

Explanations

instances of irony or paradoxes in the text

oai_token-act-pair · gpt-3.5-turbo

references to irony and paradox

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

ENG

-0.68

 controllers

-0.67

Storage

-0.67

GET

-0.65

unte

-0.64

lee

-0.64

EVA

-0.64

Crash

-0.62

artney

-0.62

Interstitial

-0.62

POSITIVE LOGITS

 juxtap

1.02

 irony

0.91

 paradox

0.86

 twist

0.81

 parallels

0.80

 mockery

0.79

Osw

0.78

bringer

0.77

 ironic

0.74

 inherent

0.74

Activations Density 0.078%

instances of irony or paradoxes in the text

references to irony and paradox

No Comments

No Known Activations