INDEX

Explanations

instances of phrases indicating novelty or uniqueness

oai_token-act-pair · gpt-3.5-turbo

phrases indicating novelty or unprecedented experiences

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

adra

-0.62

 tomorrow

-0.61

 perpetual

-0.56

imming

-0.54

ogan

-0.53

redients

-0.52

 subset

-0.52

idi

-0.51

 Tues

-0.51

 endless

-0.51

POSITIVE LOGITS

 before

1.35

before

1.17

nor

1.14

 BEFORE

1.10

 except

0.98

 Before

0.94

 EVER

0.93

 anywhere

0.90

 beforehand

0.88

 unless

0.86

Activations Density 0.321%

instances of phrases indicating novelty or uniqueness

phrases indicating novelty or unprecedented experiences

No Comments

No Known Activations