INDEX

Explanations

acronyms starting with 'WH'

oai_token-act-pair · gpt-3.5-turbo

references to specific vulnerabilities or security issues related to "WH" entities or systems

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ãĤ¹ãĥĪ

-0.81

 Mercer

-0.78

ãĤª

-0.72

 Gillespie

-0.71

ger

-0.71

 Volks

-0.70

spection

-0.70

 Bulg

-0.69

 Belg

-0.68

ification

-0.67

POSITIVE LOGITS

ILE

1.15

YY

1.14

WH

1.04

ICH

0.99

INESS

0.94

ITNESS

0.94

LY

0.94

HA

0.93

OA

0.91

AX

0.89

Activations Density 0.008%

acronyms starting with 'WH'

references to specific vulnerabilities or security issues related to "WH" entities or systems

No Known Activations