INDEX

Explanations

phrases indicating desires or intentions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "to"

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

 Compass

-0.82

 Enhancement

-0.73

metadata

-0.67

grounds

-0.67

 Independence

-0.64

 Kinnikuman

-0.64

 Millennium

-0.64

ements

-0.61

wikipedia

-0.60

 Measures

-0.59

POSITIVE LOGITS

 spoil

1.19

 bother

1.14

 offend

1.14

 admit

1.10

 waste

1.09

 spend

1.08

 hear

1.07

 lose

1.03

 burden

1.01

 risk

1.00

Activations Density 0.087%

phrases indicating desires or intentions

instances of the word "to"

No Comments

No Known Activations