INDEX

Explanations

common phrases associated with possibility and potential

oai_token-act-pair · gpt-3.5-turbo

phrases that express possibilities or potential 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

plates

-0.68

Sold

-0.66

Lah

-0.66

listed

-0.63

 costing

-0.63

lights

-0.61

 Carson

-0.60

 Laksh

-0.60

 cass

-0.60

 Notting

-0.58

POSITIVE LOGITS

 conceive

1.15

 quantify

1.11

 foresee

1.05

 visualize

1.05

 achieve

1.03

 recreate

1.01

 obtain

1.00

 reconcile

1.00

 derive

0.98

 speculate

0.98

Activations Density 0.102%

common phrases associated with possibility and potential

phrases that express possibilities or potential actions

No Comments

No Known Activations