INDEX

Explanations

statements about experimental design, research methods, and data analysis

oai_token-act-pair · gpt-3.5-turbo

phrases related to psychological studies and experiments

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

RIP

-0.73

sorry

-0.70

âĿ

-0.70

inventoryQuantity

-0.66

assetsadobe

-0.65

[/

-0.64

 docs

-0.63

FAR

-0.61

 obscurity

-0.61

Capital

-0.61

POSITIVE LOGITS

 randomly

1.19

 questionnaire

1.15

 simulated

1.02

 orally

0.94

 randomized

0.93

 quizz

0.91

 anonymously

0.91

 quiz

0.90

 electrodes

0.89

 verbally

0.87

Activations Density 0.313%

statements about experimental design, research methods, and data analysis

phrases related to psychological studies and experiments

No Comments

No Known Activations