INDEX

Explanations

phrases related to conducting investigations or reviews

oai_token-act-pair · gpt-3.5-turbo

phrases related to inspections and evaluations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

liners

-0.70

usha

-0.67

Reason

-0.65

 preached

-0.64

ulla

-0.63

posted

-0.63

 tropes

-0.62

oldemort

-0.62

 excuse

-0.62

 Idea

-0.58

POSITIVE LOGITS

 tests

1.41

 evaluation

1.36

 audits

1.34

 examination

1.33

 inspections

1.32

 inspection

1.31

 investigation

1.30

 testing

1.30

 survey

1.30

 feasibility

1.29

Activations Density 0.320%

phrases related to conducting investigations or reviews

phrases related to inspections and evaluations

No Comments

No Known Activations