INDEX

Explanations

phrases related to specific physical locations

oai_token-act-pair · gpt-3.5-turbo

references to medical settings and conditions related to hospitals and patient care

oai_token-act-pair · gpt-4o-mini Triggered by @bot

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

BIP

-0.87

govtrack

-0.75

votes

-0.71

gey

-0.70

ptoms

-0.66

intent

-0.66

chrom

-0.66

SVG

-0.66

gex

-0.64

Force

-0.64

POSITIVE LOGITS

 offices

1.55

 apartment

1.54

 hotels

1.51

 rooms

1.50

 residences

1.49

 hotel

1.48

 kitchens

1.45

 apartments

1.44

 bedrooms

1.44

 warehouses

1.42

Activations Density 1.456%

phrases related to specific physical locations

references to medical settings and conditions related to hospitals and patient care

No Comments

No Known Activations