INDEX

Explanations

phrases related to long-term impact or duration

oai_token-act-pair · gpt-3.5-turbo

references to long-term effects or implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Scrib

-0.95

 Compass

-0.94

Wiz

-0.85

 GEAR

-0.82

Pok

-0.80

ADRA

-0.79

 Dickinson

-0.75

 Polo

-0.75

 Solitaire

-0.75

ulhu

-0.74

POSITIVE LOGITS

term

1.30

distance

1.20

enough

1.18

haired

1.12

lasting

1.10

sighted

1.09

eyed

1.07

suff

1.07

tailed

1.06

circ

1.06

Activations Density 0.039%

phrases related to long-term impact or duration

references to long-term effects or implications

No Comments

No Known Activations