INDEX

Explanations

specific mentions of car brands and models

oai_token-act-pair · gpt-3.5-turbo

specific car brands and models mentioned in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

sites

-0.90

papers

-0.90

 Flavoring

-0.87

abilities

-0.77

 pores

-0.73

glers

-0.73

utenberg

-0.72

abases

-0.70

iotics

-0.70

redients

-0.70

POSITIVE LOGITS

 sedan

1.48

SUV

1.30

 convertible

1.28

GT

1.10

 Cherokee

1.09

 Corvette

1.07

 dealership

1.06

 wagon

1.05

 Mustang

1.05

 Convert

1.04

Activations Density 0.123%

specific mentions of car brands and models

specific car brands and models mentioned in the document

No Comments

No Known Activations