INDEX

Explanations

words related to video production and film industry

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

reatment

-0.73

 therap

-0.72

informed

-0.72

 caregivers

-0.70

autions

-0.70

 behaviours

-0.69

 characteristics

-0.69

osexual

-0.69

cffffcc

-0.68

munition

-0.68

POSITIVE LOGITS

Nap

1.03

Cal

0.95

Sid

0.93

 Timber

0.92

Mal

0.92

 Orange

0.92

Pet

0.91

Nex

0.91

 Mond

0.89

 Sand

0.89

Activations Density 1.473%

words related to video production and film industry

No Comments

No Known Activations