INDEX

Explanations

words related to negative attributes or criticisms

oai_token-act-pair · gpt-3.5-turbo

words related to imbalance or imperfections

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

-0.87

ttes

-0.79

Downloadha

-0.75

DragonMagazine

-0.70

 Warwick

-0.69

 Mississ

-0.68

 slash

-0.67

 Morales

-0.67

Rav

-0.66

 Witches

-0.65

POSITIVE LOGITS

balanced

1.17

unity

1.14

itated

1.11

itating

1.09

itates

1.04

mer

1.04

mediate

1.04

medi

1.03

press

1.02

ply

1.01

Activations Density 0.007%

words related to negative attributes or criticisms

words related to imbalance or imperfections

No Comments

No Known Activations