INDEX

Explanations

phrases related to the beginning or initiation of activities or events

oai_token-act-pair · gpt-3.5-turbo

instances of the word "start" and phrases related to beginnings or initiation

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

 entirety

-0.66

selves

-0.60

ãĤĭ

-0.59

 notorious

-0.58

 Quarterly

-0.58

 surv

-0.57

æ©Ł

-0.57

 keyboards

-0.57

 majority

-0.55

 Bastard

-0.54

POSITIVE LOGITS

nings

1.32

ribune

0.99

ups

0.98

up

0.93

ners

0.92

date

0.89

 date

0.88

UP

0.87

rek

0.86

strap

0.84

Activations Density 0.050%

phrases related to the beginning or initiation of activities or events

instances of the word "start" and phrases related to beginnings or initiation

No Comments

No Known Activations