INDEX

Explanations

terms related to scientific subjects or technical processes

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

Â¯

-0.70

LET

-0.69

UTF

-0.66

ãģ¾

-0.64

-0.62

udeb

-0.61

SpaceEngineers

-0.59

PLIED

-0.58

gie

-0.58

netflix

-0.57

POSITIVE LOGITS

 Advice

1.09

 Problems

1.03

 Analysis

1.02

 Profile

1.02

 Benefits

1.02

 Overview

1.01

 Comparison

0.99

 Issues

0.98

 Versus

0.97

 Features

0.97

Activations Density 0.297%

terms related to scientific subjects or technical processes

No Comments

No Known Activations