INDEX

Explanations

names of a specific person, likely related to politics or public figures

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Paul."

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

 Mechdragon

-0.67

 MacArthur

-0.66

åĤ

-0.65

 Integrity

-0.64

 Transparency

-0.64

CLE

-0.63

Environmental

-0.63

flush

-0.63

RFC

-0.60

POSITIVE LOGITS

iflower

1.65

iffe

1.07

inations

0.98

oons

0.94

oaded

0.93

ibrary

0.91

atility

0.87

hemy

0.85

inator

0.85

itudes

0.82

Activations Density 0.013%

names of a specific person, likely related to politics or public figures

occurrences of the name "Paul."

No Comments

No Known Activations