INDEX

Explanations

phrases related to organization restructuring and categorization

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

tar

-0.74

 fortun

-0.70

linger

-0.68

 insulted

-0.66

nz

-0.65

warning

-0.64

entimes

-0.63

tor

-0.63

press

-0.63

echo

-0.63

POSITIVE LOGITS

 manageable

1.04

 thirds

0.97

 categories

0.92

 chunks

0.90

 phases

0.89

 segments

0.87

 discrete

0.86

 halves

0.85

 Pieces

0.85

 pieces

0.84

Activations Density 0.051%

phrases related to organization restructuring and categorization

No Comments

No Known Activations