INDEX

Explanations

unexpected or random occurrences within a specific context or setting

oai_token-act-pair · gpt-3.5-turbo

terms related to unexpected or unexplained events

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

angelo

-0.69

ucci

-0.56

hetti

-0.55

acebook

-0.52

soDeliveryDate

-0.52

assadors

-0.52

ilingual

-0.51

cerned

-0.50

 Ferr

-0.50

Ã®

-0.50

POSITIVE LOGITS

 Reck

0.54

 Leviathan

0.49

 reven

0.48

Pv

0.47

 Dism

0.47

Ĥİ

0.46

 Wast

0.46

earances

0.46

Cry

0.46

 Coverage

0.46

Activations Density 1.021%

unexpected or random occurrences within a specific context or setting

terms related to unexpected or unexplained events

No Comments

No Known Activations