INDEX

Explanations

terms related to social media and online presence

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

nces

-1.03

urat

-0.75

ilts

-0.75

xual

-0.72

ARDS

-0.69

 Cursed

-0.69

atche

-0.68

shall

-0.68

 Ridge

-0.67

-0.66

POSITIVE LOGITS

izing

0.98

istic

0.95

ized

0.92

ization

0.90

 networks

0.89

 norms

0.88

 networking

0.87

 democr

0.83

isms

0.83

 gatherings

0.82

Activations Density 0.387%

terms related to social media and online presence

No Comments

No Known Activations