INDEX

Explanations

phrases related to abnormality, sickness, intention, affection, environment, maniac behavior, and horrific events

oai_token-act-pair · gpt-3.5-turbo

terms related to abnormalities and emotional connections

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Genocide

-0.61

 palms

-0.60

packing

-0.57

 Cheong

-0.57

 menstrual

-0.56

rooms

-0.56

>>>>>>>>

-0.55

 Bush

-0.54

FFER

-0.54

 straw

-0.54

POSITIVE LOGITS

ally

1.98

ality

1.82

alities

1.52

ately

1.47

als

1.41

nel

1.35

alist

1.33

al

1.23

atively

1.22

arily

1.22

Activations Density 0.117%

phrases related to abnormality, sickness, intention, affection, environment, maniac behavior, and horrific events

terms related to abnormalities and emotional connections

No Comments

No Known Activations