INDEX

Explanations

decisions, results, and outcomes in a variety of contexts

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

mans

-0.76

udi

-0.72

uni

-0.72

yi

-0.70

andise

-0.70

ker

-0.70

afort

-0.69

oneliness

-0.66

ondo

-0.66

ansk

-0.65

POSITIVE LOGITS

 outcome

1.09

 outcomes

1.08

 thereof

0.98

bringer

0.89

 probabilities

0.75

 expectancy

0.73

fulness

0.71

 Winner

0.70

romeda

0.68

ality

0.67

Activations Density 0.025%

decisions, results, and outcomes in a variety of contexts

No Comments

No Known Activations