INDEX

Explanations

statistics or numerical values in the text

oai_token-act-pair · gpt-3.5-turbo

statistics and numerical data related to various trends and changes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

cott

-0.69

acebook

-0.66

cients

-0.66

ebook

-0.63

icians

-0.62

boss

-0.62

nil

-0.61

CLUD

-0.61

ĪĴ

-0.60

ACTED

-0.60

POSITIVE LOGITS

 capacity

0.79

 expectancy

0.78

 direction

0.77

ahime

0.77

 magnitude

0.71

 responsiveness

0.68

 compared

0.66

 esteem

0.64

 expenditure

0.63

 increments

0.63

Activations Density 0.300%

statistics or numerical values in the text

statistics and numerical data related to various trends and changes

No Comments

No Known Activations