INDEX

Explanations

words related to management and organizational structures

oai_token-act-pair · gpt-3.5-turbo

terms related to abnormal psychological behaviors and corporate themes

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FFER

-0.63

 mamm

-0.61

 secrets

-0.60

 heart

-0.60

âĺħâĺħ

-0.60

 dust

-0.56

UGH

-0.56

 speech

-0.56

 palms

-0.56

 chance

-0.56

POSITIVE LOGITS

ally

1.97

ality

1.86

alities

1.54

als

1.53

nel

1.45

alist

1.40

naire

1.34

ately

1.33

al

1.26

atively

1.24

Activations Density 0.104%

words related to management and organizational structures

terms related to abnormal psychological behaviors and corporate themes

No Comments

No Known Activations