INDEX

Explanations

situations or scenarios related to journalism or written articles

oai_token-act-pair · gpt-3.5-turbo

mentions of articles or written works

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 transporter

-0.74

cream

-0.70

 embryos

-0.70

lace

-0.69

 joystick

-0.68

 controls

-0.67

Ĭ±

-0.66

rollers

-0.65

ĪĴ

-0.64

elsen

-0.64

POSITIVE LOGITS

 titled

1.20

 headlined

1.02

 entitled

0.96

 penned

0.95

meal

0.91

 published

0.89

 excerpt

0.83

 essay

0.83

itled

0.80

 reprinted

0.80

Activations Density 0.069%

situations or scenarios related to journalism or written articles

mentions of articles or written works

No Comments

No Known Activations