INDEX

Explanations

words related to the name "Gwyn" with various intensities

oai_token-act-pair · gpt-3.5-turbo

references to specific names and terms related to individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

unin

-0.77

omsky

-0.70

onomic

-0.63

rero

-0.63

 predicting

-0.62

 locality

-0.62

icably

-0.62

 Uzbek

-0.61

 Lima

-0.61

onom

-0.60

POSITIVE LOGITS

wyn

1.46

robe

1.00

burn

0.89

boro

0.89

bridge

0.85

er

0.83

igans

0.81

restling

0.80

wen

0.78

yth

0.77

Activations Density 0.005%

words related to the name "Gwyn" with various intensities

references to specific names and terms related to individuals or entities

No Comments

No Known Activations