INDEX

Explanations

phrases indicating physical movement or action towards something or someone

oai_token-act-pair · gpt-3.5-turbo

instances of the word "to" suggesting directional or intended actions

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

hops

-0.75

 vows

-0.70

 phased

-0.69

RF

-0.68

packing

-0.66

listed

-0.66

soDeliveryDate

-0.65

 tours

-0.65

 licences

-0.65

reports

-0.63

POSITIVE LOGITS

ggles

1.07

othy

1.04

wered

0.97

 maximize

0.97

 minimize

0.93

 relieve

0.91

 conserve

0.88

 accommodate

0.88

 avoid

0.87

 shore

0.87

Activations Density 0.298%

phrases indicating physical movement or action towards something or someone

instances of the word "to" suggesting directional or intended actions

No Comments

No Known Activations