INDEX

Explanations

phrases denoting different names or identities for people or characters

oai_token-act-pair · gpt-3.5-turbo

the term "aka" and its associated usage in describing alternate names or aliases

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

stal

-0.79

ttes

-0.78

Ö¼

-0.76

arching

-0.71

EEE

-0.71

avorable

-0.70

aments

-0.69

iets

-0.68

zanne

-0.67

amily

-0.66

POSITIVE LOGITS

 HERO

0.83

CoC

0.81

 Chosen

0.77

 Despair

0.75

Ops

0.67

 Theft

0.66

 Lawson

0.66

 Skydragon

0.64

 Bust

0.64

 yours

0.64

Activations Density 0.016%

phrases denoting different names or identities for people or characters

the term "aka" and its associated usage in describing alternate names or aliases

No Comments

No Known Activations