INDEX

Explanations

instances of actions related to processes, agreements, and practices in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

regor

-0.63

estern

-0.58

 Desmond

-0.57

 Junk

-0.56

verbs

-0.55

ometimes

-0.55

 Toad

-0.54

idth

-0.54

 pige

-0.53

 GREAT

-0.53

POSITIVE LOGITS

.''.

0.96

 unilaterally

0.95

 altogether

0.94

0.91

.[

0.91

 sooner

0.88

.</

0.87

 anytime

0.87

 anyway

0.86

 administr

0.86

Activations Density 0.358%

instances of actions related to processes, agreements, and practices in various contexts

No Comments

No Known Activations