INDEX

Explanations

items or objects mentioned in a list

oai_token-act-pair · gpt-3.5-turbo

various types of items and topics associated with categories of social, legal, or tangible elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

lez

-0.65

 hindsight

-0.65

TW

-0.64

ixties

-0.63

nin

-0.63

nesia

-0.63

escription

-0.62

ozyg

-0.62

CHAT

-0.61

uckland

-0.61

POSITIVE LOGITS

 thereof

1.09

 alike

0.99

 pertaining

0.99

 besides

0.95

 related

0.92

 relating

0.89

 associated

0.89

 respectively

0.88

 thereto

0.80

 deemed

0.80

Activations Density 0.233%

items or objects mentioned in a list

various types of items and topics associated with categories of social, legal, or tangible elements

No Comments

No Known Activations