INDEX

Explanations

phrases related to email notifications and communication

oai_token-act-pair · gpt-3.5-turbo

indicators of optimal choices or recommendations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ividual

-0.67

ĸļ

-0.66

ãĤ¼ãĤ¦ãĤ¹

-0.64

english

-0.63

ructose

-0.63

famous

-0.62

PRESS

-0.62

 Created

-0.62

ibel

-0.62

ODUCT

-0.61

POSITIVE LOGITS

 alternatives

2.02

 options

1.87

 option

1.68

 alternative

1.62

 possibilities

1.54

 feasible

1.49

 Option

1.44

Option

1.44

 viable

1.36

 solutions

1.34

Activations Density 1.345%

phrases related to email notifications and communication

indicators of optimal choices or recommendations

No Comments

No Known Activations