INDEX

Explanations

OS as part of an abbreviation or acronyms

oai_token-act-pair · gpt-3.5-turbo

mentions of the Public Library of Science (PLOS) and its related journals

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

ered

-0.89

aneous

-0.83

ries

-0.80

ãĤ¡

-0.77

riet

-0.70

ruary

-0.69

ry

-0.67

ãĥ©ãĥ³

-0.66

rhy

-0.66

stract

-0.66

POSITIVE LOGITS

 ANGEL

1.00

ECTION

0.98

metics

0.92

DAQ

0.91

OME

0.89

hiba

0.89

HI

0.89

ystem

0.88

ynthesis

0.85

cano

0.85

Activations Density 0.015%

OS as part of an abbreviation or acronyms

mentions of the Public Library of Science (PLOS) and its related journals

No Comments

No Known Activations