INDEX

Explanations

future tense verbs

oai_token-act-pair · gpt-3.5-turbo

phrases indicating future occurrences or predictions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

buster

-0.67

cius

-0.60

strate

-0.59

pose

-0.59

 elector

-0.56

 Psychiatry

-0.55

roit

-0.55

 maze

-0.55

alloc

-0.55

zee

-0.54

POSITIVE LOGITS

 plenty

0.99

 lots

0.80

 exceptions

0.77

 some

0.76

å¥³

0.75

 ample

0.74

 SOME

0.69

 parallels

0.69

estern

0.68

 alot

0.68

Activations Density 0.051%

future tense verbs

phrases indicating future occurrences or predictions

No Comments

No Known Activations