INDEX

Explanations

mentions of the White House

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the "White House."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

NetMessage

-0.76

REG

-0.73

FORM

-0.69

hra

-0.67

#$#$

-0.66

 ILCS

-0.66

Filter

-0.65

enance

-0.63

amaz

-0.63

sin

-0.63

POSITIVE LOGITS

 Office

0.99

 Counsel

0.92

 Depot

0.88

 Painter

0.86

 Intelligence

0.86

 Correspond

0.85

 Situation

0.83

 Administration

0.83

 administrations

0.79

 Assistant

0.78

Activations Density 0.022%

mentions of the White House

repeated mentions of the "White House."

No Comments

No Known Activations