INDEX

Explanations

names of specific companies or organizations

oai_token-act-pair · gpt-3.5-turbo

names of companies and organizations, particularly in the tech and film industries

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

 appellant

-0.53

wcs

-0.52

grand

-0.51

rez

-0.50

 turtle

-0.50

 converted

-0.50

 chart

-0.49

DEC

-0.49

POSITIVE LOGITS

prototype

0.74

arenthood

0.68

ruary

0.67

folios

0.67

OPA

0.63

gins

0.63

Ã«

0.62

culosis

0.62

tsy

0.62

ãĤ¼

0.60

Activations Density 0.579%

names of specific companies or organizations

names of companies and organizations, particularly in the tech and film industries

No Comments

No Known Activations