INDEX

Explanations

phrases related to political figures and events

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_fs6144-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

6,144

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

enture

-0.82

oor

-0.79

eco

-0.78

estone

-0.74

olo

-0.72

pt

-0.71

estones

-0.70

oÄŁ

-0.70

uce

-0.69

vernight

-0.69

POSITIVE LOGITS

 namely

1.14

 albeit

0.91

Sue

0.83

Les

0.81

 Maurice

0.81

Lia

0.80

Pam

0.80

 Herb

0.80

 Pats

0.79

Ake

0.78

Activations Density 0.509%

phrases related to political figures and events

No Comments

No Known Activations