INDEX

Explanations

technical terms related to software updates and patches

oai_token-act-pair · gpt-3.5-turbo

specific updates and details related to software patches or game releases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Twain

-0.91

ogie

-0.80

 Muss

-0.79

 Sheldon

-0.76

 videot

-0.75

 Stanley

-0.73

 Witt

-0.73

 Berm

-0.71

 caric

-0.71

 photoc

-0.70

POSITIVE LOGITS

 update

1.23

fixes

1.22

 Updates

1.18

 updates

1.11

 devs

1.09

 Fixes

1.07

 fixes

1.05

 Update

1.04

 Release

1.02

 Updated

1.01

Activations Density 0.937%

technical terms related to software updates and patches

specific updates and details related to software patches or game releases

No Comments

No Known Activations