INDEX

Explanations

The neuron is looking for instances where the phrase "I mean" is used in a sentence

oai_token-act-pair · gpt-3.5-turbo

phrases indicating human behavior or inclinations

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

artifacts

-0.73

ifference

-0.70

gression

-0.68

htaking

-0.63

watching

-0.62

 threads

-0.61

 imped

-0.59

paying

-0.59

immune

-0.59

udeau

-0.58

POSITIVE LOGITS

 acronym

1.47

 slang

1.35

 moniker

1.34

 abbre

1.33

 coined

1.31

 term

1.29

 nickname

1.28

 name

1.23

 referring

1.15

 shorthand

1.14

Activations Density 0.670%

The neuron is looking for instances where the phrase "I mean" is used in a sentence

phrases indicating human behavior or inclinations

No Comments

No Known Activations