INDEX

Explanations

expressions of personal preference or opinion

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

 Hebdo

-0.67

ellar

-0.64

Gap

-0.62

VERTISEMENT

-0.62

artney

-0.59

 precursor

-0.59

Smart

-0.58

 dwind

-0.57

odder

-0.57

 Combine

-0.57

POSITIVE LOGITS

 myself

1.38

 personally

1.18

 glad

0.96

 recommend

0.90

 regret

0.85

 believe

0.83

 thankful

0.83

 wish

0.82

 think

0.82

heart

0.81

Activations Density 1.432%

expressions of personal preference or opinion

No Comments

No Known Activations