INDEX

Explanations

words indicating accuracy, correctness, or truth

oai_token-act-pair · gpt-3.5-turbo

terms related to accuracy or correctness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

venture

-0.71

wings

-0.69

unia

-0.69

ventures

-0.67

raints

-0.67

ury

-0.62

 Throne

-0.62

*/(

-0.61

queue

-0.59

bean

-0.59

POSITIVE LOGITS

 accurate

3.52

 inaccurate

2.38

 accuracy

2.16

 accurately

2.06

 correct

1.76

 precise

1.74

 inacc

1.65

 reliable

1.63

 truthful

1.57

 accur

1.56

Activations Density 0.022%

words indicating accuracy, correctness, or truth

terms related to accuracy or correctness

No Comments

No Known Activations