INDEX

Explanations

step-by-step instructions or explanations

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

 lately

-0.96

violence

-0.72

Politics

-0.72

 underestimated

-0.69

inventoryQuantity

-0.65

 existed

-0.65

nered

-0.64

endon

-0.63

 Earlier

-0.63

 Miche

-0.63

POSITIVE LOGITS

 whichever

1.10

 automatically

1.08

 thereafter

1.08

 optionally

1.07

 prest

1.04

 then

1.03

vo

1.02

 afterwards

0.94

 afterward

0.90

 immediately

0.90

Activations Density 3.048%

step-by-step instructions or explanations

No Comments

No Known Activations