INDEX

Explanations

words related to the application or utilization of knowledge or skills in various contexts

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

footed

-0.75

ument

-0.67

hoff

-0.66

OUS

-0.62

ldom

-0.61

hov

-0.61

acters

-0.60

 Indies

-0.60

hu

-0.60

tif

-0.60

POSITIVE LOGITS

 pressure

0.81

enz

0.67

 brakes

0.66

 sunscreen

0.66

achev

0.64

 Anarchy

0.64

aution

0.63

 inconsist

0.63

rences

0.62

arate

0.62

Activations Density 0.032%

words related to the application or utilization of knowledge or skills in various contexts

No Comments

No Known Activations