INDEX

Explanations

phrases related to technology and product features

oai_token-act-pair · gpt-3.5-turbo

negative signs or symbols in the context of various topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Dickinson

-0.75

 Norris

-0.66

 Confederation

-0.65

 Chero

-0.65

 sails

-0.64

 erosion

-0.63

 Arabian

-0.62

eca

-0.62

 constellation

-0.61

 nort

-0.61

POSITIVE LOGITS

based

1.07

sized

1.01

sama

0.98

=-=-=-=-=-=-=-=-

0.93

shaped

0.92

san

0.91

induced

0.91

level

0.91

related

0.90

type

0.89

Activations Density 0.389%

phrases related to technology and product features

negative signs or symbols in the context of various topics

No Comments

No Known Activations