INDEX

Explanations

phrases related to exploring possibilities or extending beyond current limits

oai_token-act-pair · gpt-3.5-turbo

phrases indicating limits or boundaries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

nai

-0.68

achine

-0.68

 Shinzo

-0.66

 Metatron

-0.66

MpServer

-0.65

onen

-0.64

 Unch

-0.62

 followed

-0.62

MFT

-0.61

 ACPI

-0.61

POSITIVE LOGITS

 confines

1.05

 bounds

0.99

 borders

0.90

 boundaries

0.86

 realm

0.85

 scope

0.83

 limitations

0.82

 limitation

0.82

 limits

0.79

 usual

0.78

Activations Density 0.154%

phrases related to exploring possibilities or extending beyond current limits

phrases indicating limits or boundaries

No Comments

No Known Activations