INDEX

Explanations

words related to electronic communication and actions involving sending or receiving information

oai_token-act-pair · gpt-3.5-turbo

words related to forms and suffixes in English

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

pport

-0.67

 nerv

-0.66

hus

-0.63

zan

-0.61

QUI

-0.61

bite

-0.60

gas

-0.60

odox

-0.59

andra

-0.59

bush

-0.58

POSITIVE LOGITS

 INTO

0.90

 Away

0.76

 Into

0.74

 Ahead

0.68

forward

0.66

 onward

0.66

 authenticated

0.63

 undone

0.63

 Signed

0.63

engers

0.62

Activations Density 0.098%

words related to electronic communication and actions involving sending or receiving information

words related to forms and suffixes in English

No Comments

No Known Activations