INDEX

Explanations

mentions of official names, abbreviations, and rankings

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

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

jri

-0.70

essage

-0.68

_.

-0.67

*.

-0.66

Interstitial

-0.62

kson

-0.61

given

-0.60

/,

-0.60

 destro

-0.60

Ì¶

-0.60

POSITIVE LOGITS

pedia

0.71

Wiki

0.69

 Profile

0.65

 Releases

0.64

 Overview

0.64

 Update

0.63

 Highlights

0.62

 Picks

0.61

 Recap

0.61

Wire

0.59

Activations Density 0.533%

mentions of official names, abbreviations, and rankings

No Comments

No Known Activations