INDEX

Explanations

phrases related to email newsletters being delivered to an inbox

oai_token-act-pair · gpt-3.5-turbo

phrases related to receiving content via email subscriptions

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

 Corpor

-0.76

Ath

-0.70

pend

-0.69

skinned

-0.69

©¶æ

-0.69

Ib

-0.66

 Seraph

-0.66

 Poles

-0.66

Pf

-0.64

hig

-0.63

POSITIVE LOGITS

 inbox

1.26

email

0.95

 mailbox

0.92

inia

0.89

oire

0.86

mail

0.84

allery

0.84

romeda

0.81

ername

0.81

 Dragonbound

0.80

Activations Density 0.012%

phrases related to email newsletters being delivered to an inbox

phrases related to receiving content via email subscriptions

No Comments

No Known Activations