INDEX

Explanations

terms related to technology and infrastructure

oai_token-act-pair · gpt-3.5-turbo

terms related to various industries and sectors, including entertainment, healthcare, finance, and public service

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

alle

-0.62

é¾įå

-0.60

ãĤ¨ãĥ«

-0.56

ãĤ®

-0.53

ãĤ½

-0.53

itional

-0.53

Versions

-0.52

inarily

-0.52

ãģĦ

-0.50

ãĥ¼ãĥĨ

-0.50

POSITIVE LOGITS

 championed

0.52

(#

0.52

 circa

0.49

Â¯

0.49

=-=-=-=-

0.49

(.

0.49

âĢİ

0.48

0.47

aka

0.47

($

0.47

Activations Density 1.031%

terms related to technology and infrastructure

terms related to various industries and sectors, including entertainment, healthcare, finance, and public service

No Comments

No Known Activations