INDEX

Explanations

instances where someone is looking at someone or something closely

oai_token-act-pair · gpt-3.5-turbo

references to self-reflection and examination

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

icia

-0.70

shire

-0.66

arsity

-0.66

hers

-0.64

UME

-0.63

heit

-0.63

 depended

-0.62

ante

-0.62

anchester

-0.62

Â¯Â¯

-0.60

POSITIVE LOGITS

paren

0.94

 scoreboard

0.81

 replay

0.79

 blinking

0.74

 positives

0.72

 horizon

0.72

 possibilities

0.71

screen

0.71

 screens

0.71

 microscope

0.70

Activations Density 0.266%

instances where someone is looking at someone or something closely

references to self-reflection and examination

No Comments

No Known Activations