INDEX

Explanations

numerical estimations or cost figures

oai_token-act-pair · gpt-3.5-turbo

phrases related to estimates and projections

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ORED

-0.68

soType

-0.66

OST

-0.65

reditary

-0.63

 Partnership

-0.61

PDATE

-0.60

DAC

-0.59

gemony

-0.59

 Gems

-0.59

 Decoder

-0.58

POSITIVE LOGITS

 cost

1.17

 reach

1.16

 accommodate

1.13

 weigh

1.10

 encompass

1.07

 take

1.05

 span

1.02

 generate

1.01

 yield

1.00

 lasts

0.99

Activations Density 0.204%

numerical estimations or cost figures

phrases related to estimates and projections

No Comments

No Known Activations