INDEX

Explanations

lines of code and programming concepts related to functional programming and data structures

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_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

asca

-0.76

hement

-0.74

 spons

-0.71

 boosters

-0.65

 advis

-0.64

 incorpor

-0.64

prising

-0.64

wig

-0.64

 advoc

-0.63

 therap

-0.61

POSITIVE LOGITS

1.32

1.28

1.24

((

1.22

{}

1.21

$(

1.16

()

1.16

=(

1.15

((

1.15

1.14

Activations Density 1.875%

lines of code and programming concepts related to functional programming and data structures

No Comments

No Known Activations