INDEX

Explanations

phrases related to fundamental values or beliefs

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

pload

-0.75

peak

-0.74

 Leone

-0.74

crow

-0.69

quer

-0.67

 Carbuncle

-0.66

sburgh

-0.66

rov

-0.66

nery

-0.66

 Volunteers

-0.65

POSITIVE LOGITS

ists

1.13

ist

1.03

ism

1.01

 tenets

0.96

izing

0.94

izes

0.93

 alteration

0.91

ization

0.91

 misunderstanding

0.90

 principles

0.89

Activations Density 0.024%

phrases related to fundamental values or beliefs

No Comments

No Known Activations