INDEX

Explanations

references to how someone or something appears or is portrayed

oai_token-act-pair · gpt-3.5-turbo

descriptions that imply a comparison or likeness to other people or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 VIDEOS

-0.77

itures

-0.71

metics

-0.71

ongyang

-0.70

profits

-0.69

 leases

-0.67

words

-0.66

onds

-0.66

itals

-0.65

 PLUS

-0.65

POSITIVE LOGITS

 fearless

0.94

 heir

0.91

 traitor

0.86

 protector

0.85

 charismatic

0.85

 persona

0.85

 unemploy

0.85

 competent

0.84

 confid

0.84

 honorary

0.84

Activations Density 0.507%

references to how someone or something appears or is portrayed

descriptions that imply a comparison or likeness to other people or entities

No Comments

No Known Activations