INDEX

Explanations

brand sponsorships or endorsements in text

oai_token-act-pair · gpt-3.5-turbo

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pend

-0.85

selves

-0.82

otom

-0.77

 Pradesh

-0.74

 nerv

-0.71

juries

-0.67

 msec

-0.67

cale

-0.64

ibaba

-0.62

 COUR

-0.62

POSITIVE LOGITS

hips

1.23

orship

0.94

 sponsors

0.90

 sponsoring

0.90

 sponsorship

0.87

Spons

0.85

 sponsor

0.85

 sponsored

0.84

 Spons

0.78

sponsored

0.76

Activations Density 0.049%

brand sponsorships or endorsements in text

No Comments

No Known Activations