INDEX

Explanations

words related to advertising or promotions

oai_token-act-pair · gpt-3.5-turbo

content related to advertisements

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

assic

-0.71

 tant

-0.68

istically

-0.66

inj

-0.60

bis

-0.60

teenth

-0.60

 marsh

-0.59

amen

-0.59

 Dull

-0.57

kaya

-0.57

POSITIVE LOGITS

<|endoftext|>

1.00

qus

0.91

Comments

0.85

Advertisements

0.79

edin

0.74

 Advertisement

0.74

VERTISEMENT

0.74

Share

0.73

 Provided

0.72

Skip

0.72

Activations Density 0.014%

words related to advertising or promotions

content related to advertisements

No Comments

No Known Activations