INDEX

Explanations

phrases or words related to positive outcomes or actions

oai_token-act-pair · gpt-3.5-turbo

phrases emphasizing the concept of "good."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

eters

-0.76

âĹ¼

-0.74

ptin

-0.71

pper

-0.70

yss

-0.68

hod

-0.67

NetMessage

-0.67

agos

-0.67

Hop

-0.64

eteria

-0.64

POSITIVE LOGITS

enough

1.14

reads

1.04

 luck

0.94

 deed

0.94

 Samar

0.89

 deeds

0.89

luck

0.87

 intentions

0.86

sword

0.85

NESS

0.81

Activations Density 0.057%

phrases or words related to positive outcomes or actions

phrases emphasizing the concept of "good."

No Comments

No Known Activations