INDEX

Explanations

phrases related to giving or receiving commands or instructions

oai_token-act-pair · gpt-3.5-turbo

references to commands and directives

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

gre

-0.72

OSS

-0.71

 Alto

-0.71

allery

-0.71

Mini

-0.71

Vul

-0.68

 Hitch

-0.68

 Volks

-0.67

ackets

-0.66

adjusted

-0.66

POSITIVE LOGITS

 decree

1.04

 issued

0.96

 confir

0.92

 prohibiting

0.91

 dictated

0.91

 forb

0.90

 directing

0.87

 authorizing

0.87

 orders

0.87

 warrants

0.85

Activations Density 0.063%

phrases related to giving or receiving commands or instructions

references to commands and directives

No Comments

No Known Activations