INDEX

Explanations

future plans or possibilities mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

terms related to bids, runs, and proposals in a political or entertainment context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

verbs

-0.67

 stere

-0.59

 Tycoon

-0.56

 merchants

-0.56

 Gleaming

-0.55

wick

-0.54

 fractions

-0.54

ongs

-0.53

 Boone

-0.53

 Sina

-0.53

POSITIVE LOGITS

 someday

1.27

 anytime

1.09

 sooner

0.99

 sometime

0.95

 ASAP

0.95

 soon

0.92

 conclud

0.83

ossier

0.83

 showdown

0.74

 hereafter

0.73

Activations Density 0.511%

future plans or possibilities mentioned in the text

terms related to bids, runs, and proposals in a political or entertainment context

No Comments

No Known Activations