INDEX

Explanations

transitional phrases indicating progression or movement in a sequence or discussion

oai_token-act-pair · gpt-3.5-turbo

transitions in topics or sections of text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ãĥ´

-0.69

boro

-0.67

ardless

-0.66

sov

-0.65

ovan

-0.64

aren

-0.63

unta

-0.61

+(

-0.61

isle

-0.61

arta

-0.60

POSITIVE LOGITS

 basics

0.90

 Conclusion

0.86

âĢ¦]

0.82

 specifics

0.77

 topic

0.76

 whats

0.74

 juicy

0.74

topic

0.73

 explan

0.72

Discussion

0.71

Activations Density 0.314%

transitional phrases indicating progression or movement in a sequence or discussion

transitions in topics or sections of text

No Comments

No Known Activations