INDEX

Explanations

technical terms and concepts related to research projects and government initiatives

oai_token-act-pair · gpt-3.5-turbo

terms related to assessments, studies, and structured systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 pawn

-0.80

 recl

-0.73

 queen

-0.73

depending

-0.72

animal

-0.71

ĻĤ

-0.71

axter

-0.70

err

-0.69

 racer

-0.69

 skiing

-0.68

POSITIVE LOGITS

 Initiative

1.19

 Programme

1.14

 Project

1.11

 Program

1.08

 Fund

1.08

 Agreement

1.07

 Committee

1.06

 Suite

1.05

 Experiment

1.05

 Collection

1.03

Activations Density 0.236%

technical terms and concepts related to research projects and government initiatives

terms related to assessments, studies, and structured systems

No Comments

No Known Activations