INDEX

Explanations

adjectives related to dream-like, imaginative, and bizarre experiences

oai_token-act-pair · gpt-3.5-turbo

themes and concepts related to the surreal and fantastical

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

PLE

-0.64

IELD

-0.64

PAY

-0.63

BY

-0.63

ORD

-0.63

 Caesar

-0.63

EVA

-0.62

 Thor

-0.62

âĸ¬

-0.62

bury

-0.62

POSITIVE LOGITS

ism

2.24

ists

2.18

istic

2.14

ist

2.11

istically

2.04

isms

1.64

istical

1.64

ized

1.45

ISM

1.43

ization

1.41

Activations Density 0.051%

adjectives related to dream-like, imaginative, and bizarre experiences

themes and concepts related to the surreal and fantastical

No Comments

No Known Activations