INDEX

Explanations

phrases related to university names and affiliations

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

elist

-0.89

gers

-0.87

emic

-0.86

erness

-0.83

els

-0.78

uel

-0.76

ers

-0.75

ems

-0.75

selection

-0.74

emark

-0.73

POSITIVE LOGITS

 Mellon

1.05

 Institution

0.93

negie

0.89

 Peninsula

0.84

idates

0.71

 Seym

0.71

itone

0.68

 PARK

0.67

Plex

0.66

pton

0.66

Activations Density 0.062%

phrases related to university names and affiliations

No Comments

No Known Activations