INDEX

Explanations

events or activities mentioned in text

oai_token-act-pair · gpt-3.5-turbo

mentions of events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Downloadha

-0.88

chery

-0.80

aunder

-0.77

 REUTERS

-0.77

ighter

-0.76

obbies

-0.75

ully

-0.75

GH

-0.75

iage

-0.73

ÄŁ

-0.73

POSITIVE LOGITS

 Commands

0.97

 Entity

0.97

 Authority

0.94

 Ribbon

0.93

 Components

0.92

 Prediction

0.91

 Event

0.91

 Coordinator

0.90

 Presence

0.90

 Framework

0.90

Activations Density 0.026%

events or activities mentioned in text

mentions of events

No Comments

No Known Activations