INDEX

Explanations

keywords related to specific projects or initiatives

oai_token-act-pair · gpt-3.5-turbo

specific terms related to projects, entities, and systems in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

yond

-0.90

theless

-0.87

anton

-0.83

pse

-0.82

nos

-0.80

utf

-0.79

 livest

-0.78

angible

-0.77

 acad

-0.77

 skelet

-0.75

POSITIVE LOGITS

 Appeal

1.24

 Program

1.22

 Module

1.21

 Pool

1.20

 Campaign

1.18

 Programme

1.18

 Practice

1.17

 Project

1.17

 System

1.17

 Movement

1.17

Activations Density 0.209%

keywords related to specific projects or initiatives

specific terms related to projects, entities, and systems in various contexts

No Comments

No Known Activations