INDEX

Explanations

phrases related to advertisements

oai_token-act-pair · gpt-3.5-turbo

mentions of advertisements

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

ĨĴ

-0.80

uckle

-0.80

 Citation

-0.77

GoldMagikarp

-0.69

ĸļ

-0.69

ource

-0.66

 Caribbean

-0.65

ESSION

-0.65

 Remem

-0.65

POSITIVE LOGITS

verts

1.11

hoc

1.11

vertising

1.11

elaide

1.10

roit

1.06

 nause

1.03

verb

0.99

vertis

0.99

ieu

0.98

idas

0.97

Activations Density 0.019%

phrases related to advertisements

mentions of advertisements

No Comments

No Known Activations