INDEX

Explanations

descriptions of different countries and prominent figures associated with them

oai_token-act-pair · gpt-3.5-turbo

references to notable places, entities, and their status or rankings in the world

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Norn

-0.72

 Dover

-0.67

 Duffy

-0.66

DAV

-0.63

 thence

-0.61

livion

-0.60

NAV

-0.60

 Compass

-0.60

 Purs

-0.60

PUR

-0.58

POSITIVE LOGITS

iest

0.77

 favorites

0.76

abouts

0.74

 quir

0.72

 favourites

0.71

few

0.69

ils

0.69

 incarn

0.68

ipal

0.68

osponsors

0.67

Activations Density 0.407%

descriptions of different countries and prominent figures associated with them

references to notable places, entities, and their status or rankings in the world

No Comments

No Known Activations