INDEX

Explanations

mentions of awards and accolades

oai_token-act-pair · gpt-3.5-turbo

terms associated with awards and recognitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 squats

-0.79

 arriving

-0.73

 waking

-0.71

 clinging

-0.71

 transfers

-0.70

piv

-0.70

 overth

-0.70

umb

-0.70

 brute

-0.69

 signs

-0.68

POSITIVE LOGITS

 Excellence

1.33

 UNESCO

1.28

 Best

1.26

 Pulitzer

1.17

Best

1.17

 Award

1.15

 Editors

1.14

 Lifetime

1.12

 prestigious

1.12

 Awards

1.12

Activations Density 0.307%

mentions of awards and accolades

terms associated with awards and recognitions

No Comments

No Known Activations