INDEX

Explanations

phrases related to politics and political figures

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

 clitor

-0.79

 pigeon

-0.76

 reflex

-0.70

 peripheral

-0.69

 lapse

-0.68

 subp

-0.67

 territorial

-0.67

 mounts

-0.66

 avenues

-0.66

 trail

-0.65

POSITIVE LOGITS

ï¸ı

1.47

ternity

1.04

ï¸

0.91

there

0.91

âĶĢâĶĢ

0.91

uthor

0.89

amily

0.88

then

0.84

ł

0.82

conom

0.81

Activations Density 0.369%

phrases related to politics and political figures

No Comments

No Known Activations