INDEX

Explanations

various technical and usability-related terms and issues within a text

oai_token-act-pair · gpt-3.5-turbo

terms related to performance and usability metrics in various contexts

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

renheit

-0.69

cart

-0.67

 Roof

-0.66

estead

-0.65

llan

-0.64

 ENTER

-0.64

onymous

-0.64

 Telephone

-0.62

enium

-0.62

deen

-0.62

POSITIVE LOGITS

 issues

1.52

 considerations

1.52

 inconsistencies

1.38

 discrepancies

1.37

 woes

1.37

 problems

1.34

 irregularities

1.32

 tweaks

1.32

 constraints

1.32

 implications

1.32

Activations Density 0.406%

various technical and usability-related terms and issues within a text

terms related to performance and usability metrics in various contexts

No Comments

No Known Activations