INDEX

Explanations

instances of the word "unconscious" and related concepts

oai_token-act-pair · gpt-3.5-turbo

terms related to states of unconsciousness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

mm

-0.68

pher

-0.67

 premier

-0.67

lv

-0.66

mite

-0.65

 Contra

-0.65

ium

-0.64

 sold

-0.63

ÙĲ

-0.62

haw

-0.62

POSITIVE LOGITS

 unconscious

4.20

 subconscious

2.37

 unconsciously

1.79

 conscious

1.63

conscious

1.58

 consciousness

1.43

 incapac

1.36

 asleep

1.34

 lifeless

1.19

 psyche

1.19

Activations Density 0.025%

instances of the word "unconscious" and related concepts

terms related to states of unconsciousness

No Comments

No Known Activations