INDEX

Explanations

phrases related to waking up or becoming aware of something

oai_token-act-pair · gpt-3.5-turbo

instances of the word "woke" and its variations related to awakening or realization

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 negatives

-0.68

 excellence

-0.64

vg

-0.63

 Monaco

-0.62

 fines

-0.61

 Citation

-0.61

oles

-0.61

 interpol

-0.61

[*]

-0.60

iar

-0.60

POSITIVE LOGITS

 woke

3.49

 awoke

3.20

 waking

2.88

 wakes

2.83

 awake

2.75

 awakened

2.71

 awoken

2.46

 awaken

2.34

 wake

2.32

 awakening

2.05

Activations Density 0.029%

phrases related to waking up or becoming aware of something

instances of the word "woke" and its variations related to awakening or realization

No Comments

No Known Activations