INDEX

Explanations

words related to communication with emphasis or affirmation

oai_token-act-pair · gpt-3.5-turbo

conversational phrases that express humor or sarcasm

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

pires

-0.73

minster

-0.66

Interestingly

-0.63

³

-0.62

abase

-0.61

Hack

-0.60

Result

-0.60

aneous

-0.60

lier

-0.59

Page

-0.59

POSITIVE LOGITS

 please

1.02

_-

1.00

 lest

1.00

 unless

0.99

 because

0.89

unless

0.87

 they

0.84

it

0.83

we

0.83

 otherwise

0.82

Activations Density 0.267%

words related to communication with emphasis or affirmation

conversational phrases that express humor or sarcasm

No Comments

No Known Activations