INDEX

Explanations

positive words or phrases

oai_token-act-pair · gpt-3.5-turbo

expressions of positive sentiment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

loo

-0.73

 Hearts

-0.69

HAEL

-0.69

wine

-0.69

opsy

-0.68

 Brilliant

-0.67

ARDS

-0.64

AMES

-0.64

doms

-0.63

spo

-0.63

POSITIVE LOGITS

itional

1.63

itions

1.52

itivity

1.30

idon

1.21

itor

1.15

itive

1.15

itionally

1.15

itives

1.14

itory

1.13

icion

1.13

Activations Density 0.059%

positive words or phrases

expressions of positive sentiment

No Comments

No Known Activations