INDEX

Explanations

phrases related to specific locations or roles within an organization

oai_token-act-pair · gpt-3.5-turbo

terms associated with positions or roles in organizations and competitive contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

anson

-0.51

lif

-0.51

cern

-0.50

vae

-0.50

psc

-0.50

wic

-0.50

ļé

-0.50

NetMessage

-0.49

ewitness

-0.49

userc

-0.48

POSITIVE LOGITS

 aisle

0.66

iest

0.65

 throne

0.59

 fraternity

0.57

forts

0.57

liest

0.57

eers

0.56

IPM

0.56

 portion

0.56

finals

0.54

Activations Density 0.465%

phrases related to specific locations or roles within an organization

terms associated with positions or roles in organizations and competitive contexts

No Comments

No Known Activations