INDEX

Explanations

phrases related to official statements or quotes from various entities

oai_token-act-pair · gpt-3.5-turbo

the word "in."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

-0.77

wagon

-0.68

 lasted

-0.65

killed

-0.64

 enjoys

-0.62

 lasts

-0.62

ens

-0.59

 Entered

-0.59

 knows

-0.59

 incumb

-0.58

POSITIVE LOGITS

 lieu

1.22

 unison

1.00

clus

0.93

 conjunction

0.89

 terms

0.88

aug

0.88

versely

0.88

 advance

0.88

 order

0.86

 vain

0.86

Activations Density 0.068%

phrases related to official statements or quotes from various entities

the word "in."

No Comments

No Known Activations