INDEX

Explanations

phrases related to pushing boundaries and limits

oai_token-act-pair · gpt-3.5-turbo

phrases centered around pushing limits and boundaries

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

nces

-0.81

SEA

-0.80

enf

-0.71

FORE

-0.69

ctuary

-0.67

Û

-0.66

ffe

-0.65

cise

-0.65

efe

-0.63

rences

-0.62

POSITIVE LOGITS

 boundaries

1.06

 envelope

1.01

 agendas

0.89

 agenda

0.87

 buttons

0.83

 harder

0.82

 wedge

0.81

 forward

0.79

 onward

0.78

 forwards

0.75

Activations Density 0.156%

phrases related to pushing boundaries and limits

phrases centered around pushing limits and boundaries

No Comments

No Known Activations