INDEX

Explanations

words related to predictions or expectations

oai_token-act-pair · gpt-3.5-turbo

phrases related to expectations or predictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

çīĪ

-0.64

illery

-0.52

Interested

-0.51

riad

-0.51

everal

-0.50

uman

-0.49

vae

-0.48

oway

-0.48

redients

-0.48

retty

-0.48

POSITIVE LOGITS

to

1.27

to

1.07

TO

0.88

To

0.84

To

0.83

 thereto

0.72

gradation

0.70

ta

0.68

 unto

0.61

TO

0.60

Activations Density 0.333%

words related to predictions or expectations

phrases related to expectations or predictions

No Comments

No Known Activations