INDEX

Explanations

content related to media production, film, television, and interviews

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

hered

-0.71

odcast

-0.70

ANC

-0.70

uta

-0.69

uty

-0.67

OND

-0.66

owered

-0.66

 Powered

-0.66

UC

-0.66

DX

-0.64

POSITIVE LOGITS

 secondly

1.28

 THEN

1.26

 then

1.23

 therefore

1.22

 thus

1.19

 hence

1.19

 consequently

1.16

 blah

1.14

romeda

1.13

 thats

1.08

Activations Density 1.085%

content related to media production, film, television, and interviews

No Comments

No Known Activations