INDEX

Explanations

expressions indicating cause and effect

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate cause and effect relationships

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

Magn

-0.67

 Armenia

-0.66

 Tsukuyomi

-0.65

opal

-0.65

 Tian

-0.62

emetery

-0.62

oulder

-0.62

 Flavoring

-0.62

ishops

-0.61

 Medal

-0.59

POSITIVE LOGITS

Ĥİ

0.70

ociation

0.70

lie

0.70

 guise

0.69

loo

0.65

phony

0.64

©¶æ¥µ

0.64

uating

0.62

querque

0.61

 guiActiveUn

0.61

Activations Density 0.036%

expressions indicating cause and effect

phrases that indicate cause and effect relationships

No Comments

No Known Activations