INDEX

Explanations

words related to location or position, especially indicating high importance or relevance

oai_token-act-pair · gpt-3.5-turbo

positional or directional words indicating movement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

acco

-0.66

igmat

-0.66

oidal

-0.65

ometric

-0.64

oult

-0.64

erest

-0.63

chio

-0.62

actic

-0.62

ictive

-0.62

ocratic

-0.61

POSITIVE LOGITS

rompt

0.79

\\\\\\\\\\\\\\\\

0.71

©¶æ

0.70

edIn

0.69

etheless

0.69

eatures

0.68

stairs

0.67

falls

0.64

 Ramadan

0.62

 Noon

0.62

Activations Density 0.275%

words related to location or position, especially indicating high importance or relevance

positional or directional words indicating movement

No Comments

No Known Activations