INDEX

Explanations

references to events or organizations in various 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Leilan

-0.64

 ceilings

-0.63

 heights

-0.58

ulner

-0.58

 Predators

-0.57

izu

-0.57

liam

-0.56

culosis

-0.56

oir

-0.55

 Shap

-0.55

POSITIVE LOGITS

meal

0.86

ridge

0.82

displayText

0.77

furt

0.73

aking

0.73

heartedly

0.70

etsu

0.67

ridges

0.67

dated

0.67

lined

0.66

Activations Density 0.017%

references to events or organizations in various contexts

No Comments

No Known Activations

references to events or organizations in various contexts

No Comments

No Known Activations