INDEX

Explanations

words related to allowing or enabling someone to do something

oai_token-act-pair · gpt-3.5-turbo

pronouns referring to people or entities in various contexts

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

etheless

-0.82

é¾įå¥ĳå£«

-0.75

ELD

-0.73

-0.68

expected

-0.66

quickShipAvailable

-0.66

ebus

-0.65

ENDED

-0.64

WARD

-0.63

anticipated

-0.63

POSITIVE LOGITS

 shine

1.17

 dictate

1.09

 breathe

1.06

 expire

1.06

 slide

1.05

 roam

1.02

 decide

0.99

 know

0.99

 loose

0.99

 lapse

0.98

Activations Density 0.067%

words related to allowing or enabling someone to do something

pronouns referring to people or entities in various contexts

No Comments

No Known Activations