INDEX

Explanations

technical terms and features that enhance user experience

oai_token-act-pair · gpt-3.5-turbo

references to the quantity and diversity of features or elements in a context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

gypt

-0.82

anus

-0.73

lus

-0.73

ale

-0.73

ensis

-0.72

nea

-0.72

aeus

-0.70

 thence

-0.69

minimum

-0.68

©¶æ

-0.68

POSITIVE LOGITS

 surprises

1.43

 advantages

1.26

 similarities

1.24

 possibilities

1.24

 extras

1.22

 interesting

1.21

 options

1.18

 modifications

1.18

 optimizations

1.17

 goodies

1.16

Activations Density 0.280%

technical terms and features that enhance user experience

references to the quantity and diversity of features or elements in a context

No Comments

No Known Activations