INDEX

Explanations

verbs related to testing and assessment

oai_token-act-pair · gpt-3.5-turbo

references to testing and evaluation 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

lance

-0.75

CHAPTER

-0.70

\">

-0.70

 Author

-0.68

 Editorial

-0.67

displayText

-0.67

anza

-0.66

fur

-0.66

('

-0.66

ãĥ£

-0.63

POSITIVE LOGITS

 hypotheses

0.99

 readiness

0.91

worthiness

0.84

 viability

0.83

 hypothesis

0.83

 feasibility

0.81

formance

0.79

 patience

0.73

 validity

0.71

 chops

0.71

Activations Density 0.195%

verbs related to testing and assessment

references to testing and evaluation in various contexts

No Comments

No Known Activations