INDEX

Explanations

phrases related to comparisons or categories

oai_token-act-pair · gpt-3.5-turbo

topics related to comparisons and categories

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ciation

-0.34

inventoryQuantity

-0.34

ibles

-0.31

cigarettes

-0.29

omics

-0.29

arrell

-0.29

rin

-0.29

 guiActiveUnfocused

-0.28

annie

-0.28

gments

-0.27

POSITIVE LOGITS

 withd

0.31

 cryst

0.31

 exha

0.29

 âĶľ

0.28

 embr

0.27

 commun

0.27

iosyn

0.26

 Amon

0.26

 energetic

0.26

 vulner

0.26

Activations Density 5.515%

phrases related to comparisons or categories

topics related to comparisons and categories

No Comments

No Known Activations