INDEX

Explanations

mentions of someone's name followed by a verb indicating an action

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "we."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 gratification

-0.81

ional

-0.71

 citations

-0.68

 contradictions

-0.68

quo

-0.67

 pedoph

-0.62

 derail

-0.62

 citation

-0.62

 sucker

-0.60

 conflicts

-0.60

POSITIVE LOGITS

bsite

1.51

eping

1.27

igh

1.15

aving

1.14

akening

1.09

aning

1.08

lder

1.07

aker

1.07

arers

1.06

akens

1.06

Activations Density 0.052%

mentions of someone's name followed by a verb indicating an action

the repeated use of the word "we."

No Comments

No Known Activations