INDEX

Explanations

information related to geopolitical conflicts and humanitarian issues

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

 ogre

-0.77

 affili

-0.72

 pudding

-0.72

 dimensional

-0.71

»Ĵ

-0.70

hug

-0.69

 purse

-0.69

 bang

-0.69

 tremend

-0.68

gut

-0.68

POSITIVE LOGITS

 However

1.66

 Though

1.47

 Although

1.45

 They

1.44

 Meanwhile

1.43

 Additionally

1.43

 Those

1.42

 Previously

1.41

 According

1.40

 Initially

1.39

Activations Density 2.532%

information related to geopolitical conflicts and humanitarian issues

No Comments

No Known Activations