INDEX

Explanations

numerical figures or codes

oai_token-act-pair · gpt-3.5-turbo

references to communication or letters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Want

-0.58

.''.

-0.55

 attRot

-0.49

.ï¿½

-0.49

advertising

-0.49

 wanna

-0.49

.:

-0.48

.ãĢį

-0.48

.","

-0.48

XD

-0.48

POSITIVE LOGITS

Ô

0.60

aturdays

0.58

DeliveryDate

0.57

ificantly

0.55

èĢħ

0.52

versible

0.52

ometime

0.52

-,

0.51

odox

0.51

ãĥĺãĥ©

0.51

Activations Density 1.646%

numerical figures or codes

references to communication or letters

No Comments

No Known Activations