INDEX

Explanations

names or words related to individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns referring to individuals and their affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ship

-0.69

OLOGY

-0.68

ALLY

-0.67

ATTLE

-0.66

LESS

-0.65

LINE

-0.64

istically

-0.62

EEE

-0.61

ASED

-0.60

 exception

-0.60

POSITIVE LOGITS

ilver

1.40

cript

1.29

hift

1.27

kaya

1.27

aurus

1.24

pite

1.24

pring

1.24

ource

1.22

hirt

1.22

omething

1.22

Activations Density 0.190%

names or words related to individuals

proper nouns referring to individuals and their affiliations

No Comments

No Known Activations