INDEX

Explanations

words related to historical events and military operations

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

 Clash

-0.62

++++++++++++++++

-0.60

ITED

-0.59

ZA

-0.59

INC

-0.58

 sterling

-0.58

 rake

-0.57

 segregated

-0.57

 mosaic

-0.57

 cubes

-0.57

POSITIVE LOGITS

ulhu

1.52

ttp

1.43

orne

1.19

istle

1.11

umbnail

1.10

ieves

1.06

ousand

1.05

irteen

1.04

ousands

1.03

irty

1.03

Activations Density 0.029%

words related to historical events and military operations

No Comments

No Known Activations