INDEX

Explanations

items in a list

oai_token-act-pair · gpt-3.5-turbo

the phrase "list of" followed by various types of entities or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ÃĥÃĤ

-0.68

entimes

-0.63

 thrive

-0.63

etz

-0.62

 detectors

-0.60

 sensed

-0.60

irs

-0.60

 overest

-0.59

 depended

-0.59

 contam

-0.58

POSITIVE LOGITS

 sorts

0.94

éĹĺ

0.76

enance

0.73

 HERO

0.72

 course

0.68

 Excellence

0.66

worthiness

0.65

çĦ

0.63

ãĥ¼ãĥ³

0.61

RTX

0.61

Activations Density 0.329%

items in a list

the phrase "list of" followed by various types of entities or items

No Comments

No Known Activations