INDEX

Explanations

phrases related to news reports or articles written by a specific author named WR

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

omorphic

-0.81

asia

-0.70

PsyNetMessage

-0.68

iasis

-0.68

pora

-0.67

oleon

-0.65

ogly

-0.65

onic

-0.64

 incent

-0.64

eers

-0.64

POSITIVE LOGITS

DW

0.91

TI

0.88

MJ

0.85

ORD

0.83

BY

0.83

ILD

0.80

TB

0.79

ONG

0.78

FFER

0.77

ACK

0.77

Activations Density 0.044%

phrases related to news reports or articles written by a specific author named WR

No Comments

No Known Activations