INDEX

Explanations

company names

oai_token-act-pair · gpt-3.5-turbo

pharmaceutical terms and references to drug approvals

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

 "$:/

-0.84

geries

-0.84

izoph

-0.76

soDeliveryDate

-0.70

ocument

-0.66

Cth

-0.66

olation

-0.65

Interstitial

-0.65

olated

-0.65

qqa

-0.65

POSITIVE LOGITS

 Holdings

1.24

 subsidiary

1.20

 Corp

1.19

CEO

1.17

 announced

1.15

 shareholders

1.15

 employs

1.10

 executives

1.08

 declined

1.06

 subsidiaries

1.05

Activations Density 0.350%

company names

pharmaceutical terms and references to drug approvals

No Comments

No Known Activations