INDEX

Explanations

phrases related to legal and law enforcement actions

oai_token-act-pair · gpt-3.5-turbo

occurrences of commas in a list-like format

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

¬¼

-0.80

ity

-0.72

 sunset

-0.70

washer

-0.67

endo

-0.66

ishment

-0.65

ifice

-0.64

GMT

-0.62

earable

-0.62

igen

-0.62

POSITIVE LOGITS

who

1.27

doms

1.12

 whom

1.09

who

1.07

 including

1.02

whose

0.92

particularly

0.90

 rejoice

0.90

 alike

0.90

including

0.83

Activations Density 0.367%

phrases related to legal and law enforcement actions

occurrences of commas in a list-like format

No Comments

No Known Activations