INDEX

Explanations

statements or declarations made by individuals

oai_token-act-pair · gpt-3.5-turbo

instances of the word "stated" and its frequent use in formal 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Carbuncle

-0.80

xtap

-0.74

 Dome

-0.68

 Torn

-0.67

imet

-0.65

avascript

-0.64

sites

-0.63

estern

-0.62

Haz

-0.60

 wrink

-0.59

POSITIVE LOGITS

gow

0.91

 unequivocally

0.84

ance

0.83

 bluntly

0.77

 emphatically

0.74

ances

0.73

 plainly

0.73

 aloud

0.71

idate

0.69

orically

0.67

Activations Density 0.033%

statements or declarations made by individuals

instances of the word "stated" and its frequent use in formal contexts

No Comments

No Known Activations