INDEX

Explanations

phrases related to political positions and directives

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

ibaba

-0.97

etsk

-0.71

abi

-0.71

ovsky

-0.63

ashtra

-0.61

burgh

-0.60

agascar

-0.58

endas

-0.57

oÄŁ

-0.56

 worshipped

-0.56

POSITIVE LOGITS

 margins

0.94

 margin

0.84

 standards

0.84

 virtue

0.78

 means

0.76

 Means

0.72

committee

0.71

 Numbers

0.71

 sheer

0.68

 standpoint

0.63

Activations Density 0.888%

phrases related to political positions and directives

No Comments

No Known Activations