INDEX

Explanations

references to works or characters by William Shakespeare

oai_token-act-pair · gpt-3.5-turbo

references to Shakespeare and his works

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

secut

-0.75

eanor

-0.71

ramid

-0.71

achev

-0.66

igun

-0.66

ertodd

-0.65

nesty

-0.64

lopp

-0.63

veland

-0.63

apse

-0.62

POSITIVE LOGITS

 Shakespeare

0.88

 Plays

0.85

 productions

0.77

 Festival

0.77

wright

0.76

 Theatre

0.73

shire

0.73

 Mysteries

0.71

writers

0.70

acus

0.70

Activations Density 0.021%

references to works or characters by William Shakespeare

references to Shakespeare and his works

No Comments

No Known Activations