INDEX

Explanations

mentions of events or occurrences starting from a specific time point

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

pta

-0.80

BILITIES

-0.71

abus

-0.69

anie

-0.67

amina

-0.65

vantage

-0.64

abor

-0.64

potion

-0.62

natureconservancy

-0.62

Choice

-0.62

POSITIVE LOGITS

rely

1.43

 inception

1.03

0.87

0.85

0.84

0.83

 October

0.83

0.82

 infancy

0.82

Activations Density 0.305%

mentions of events or occurrences starting from a specific time point

No Comments

No Known Activations